Transfer_Learning
-
Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language Models
2025-08-18 12:00:09Dexia Chen, Wentao Zhang, Qianjie Zhu, Ping Hu, Weibing Li, Tong Zhang, Ruixuan WangAbstract
Vision-language models (VLMs) pre-trained on natural image and language data, such as CLIP, have exhibited significant potential in few-shot image recognition tasks, leading to development of various efficient transfer learning methods. These methods exploit inherent pre-learned knowledge in VLMs and have achieved strong performance on standard image datasets. However, their effectiveness is often limited when confronted with cross-domain tasks where imaging domains differ from natural images. To address this limitation, we propose Consistency-guided Multi-view Collaborative Optimization (CoMuCo), a novel fine-tuning strategy for VLMs. This strategy employs two functionally complementary expert modules to extract multi-view features, while incorporating prior knowledge-based consistency constraints and information geometry-based consensus mechanisms to enhance the robustness of feature learning. Additionally, a new cross-domain few-shot benchmark is established to help comprehensively evaluate methods on imaging domains distinct from natural images. Extensive empirical evaluations on both existing and newly proposed benchmarks suggest CoMuCo consistently outperforms current methods in few-shot tasks. The code and benchmark will be released.
Abstract (translated)
预训练于自然图像和语言数据上的视觉-语言模型（VLMs，如CLIP），在少量样本的图像识别任务中展现了巨大的潜力，并促进了各种高效迁移学习方法的发展。这些方法利用了VLMs内部预先学习的知识，在标准图像数据集上取得了强劲的表现。然而，当面对跨域任务时，即成像领域与自然图像不同，它们的有效性往往受到限制。 为了解决这一局限性，我们提出了一种新的微调策略：一致性引导的多视图协同优化（CoMuCo）。该策略采用两个功能互补的专家模块来提取多视图特征，并通过引入基于先验知识的一致性约束以及基于信息几何的共识机制，增强了特征学习的鲁棒性。此外，我们还建立了一个新的跨域少量样本基准测试集，以便全面评估那些与自然图像领域不同的成像领域的方法。 在现有和新提出的基准上进行广泛的经验评测表明，CoMuCo在少量样本任务中始终优于当前的方法。代码和基准将在不久的将来发布。
URL
https://arxiv.org/abs/2508.12861
PDF
-
Skin Cancer Classification: Hybrid CNN-Transformer Models with KAN-Based Fusion
2025-08-17 19:57:34Shubhi Agarwal, Amulya Kumar MahtoAbstract
Skin cancer classification is a crucial task in medical image analysis, where precise differentiation between malignant and non-malignant lesions is essential for early diagnosis and treatment. In this study, we explore Sequential and Parallel Hybrid CNN-Transformer models with Convolutional Kolmogorov-Arnold Network (CKAN). Our approach integrates transfer learning and extensive data augmentation, where CNNs extract local spatial features, Transformers model global dependencies, and CKAN facilitates nonlinear feature fusion for improved representation learning. To assess generalization, we evaluate our models on multiple benchmark datasets (HAM10000,BCN20000 and PAD-UFES) under varying data distributions and class imbalances. Experimental results demonstrate that hybrid CNN-Transformer architectures effectively capture both spatial and contextual features, leading to improved classification performance. Additionally, the integration of CKAN enhances feature fusion through learnable activation functions, yielding more discriminative representations. Our proposed approach achieves competitive performance in skin cancer classification, demonstrating 92.81% accuracy and 92.47% F1-score on the HAM10000 dataset, 97.83% accuracy and 97.83% F1-score on the PAD-UFES dataset, and 91.17% accuracy with 91.79% F1- score on the BCN20000 dataset highlighting the effectiveness and generalizability of our model across diverse datasets. This study highlights the significance of feature representation and model design in advancing robust and accurate medical image classification.
Abstract (translated)
皮肤癌分类是医学图像分析中的关键任务，准确地区分恶性病变和非恶性病变对于早期诊断和治疗至关重要。在这项研究中，我们探讨了结合卷积柯尔莫哥洛夫-阿恩德网络（CKAN）的序列和并行混合CNN-Transformer模型。我们的方法整合了迁移学习和广泛的数据增强技术，其中CNN用于提取局部空间特征，Transformer用于建模全局依赖关系，而CKAN通过可学习的激活函数促进非线性特征融合，以改进表示学习。 为了评估泛化能力，我们使用多个基准数据集（HAM10000、BCN20000和PAD-UFES）在不同的数据分布和类别不平衡情况下对我们的模型进行评价。实验结果显示，混合CNN-Transformer架构能够有效捕捉空间特征和上下文信息，从而提高分类性能。此外，CKAN的集成通过可学习的激活函数增强了特征融合功能，生成了更具区分性的表示。 我们提出的这种方法在皮肤癌分类中表现出色，在HAM10000数据集上达到了92.81%的准确率和92.47%的F1分数，在PAD-UFES数据集上分别达到97.83%的准确率和97.83%的F1分数，以及在BCN20000数据集上实现了91.17%的准确率和91.79%的F1分数。这些结果突显了我们模型在不同数据集中具有有效性和泛化能力。 这项研究强调了特征表示和模型设计对于提高医学图像分类鲁棒性和准确性的重要性。
URL
https://arxiv.org/abs/2508.12484
PDF
-
SemPT: Semantic Prompt Tuning for Vision-Language Models
2025-08-14 13:41:59Xiao Shi, Yangjun Ou, Zhenzhong ChenAbstract
Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language Models (VLMs) pre-trained on large amounts of image-text pairs offer a promising solution. However, existing prompt tuning methods rely on sparse category labels or disparate LLM-generated descriptions, which fragment knowledge representation and hinder transferability. To address this limitation, we introduce Semantic Prompt Tuning (SemPT), a novel framework that tackles the generalization challenge by leveraging shared attribute-level knowledge across categories. Specifically, SemPT adopts a two-step prompting strategy to guide LLM in extracting shared visual attributes and generating attribute-level descriptions, capturing transferable semantic cues beyond labels while ensuring coherent structure. Then, visually guided weighting is applied to the embeddings of attribute-level descriptions to reduce noise from irrelevant attributes and enhance the text embeddings. Additionally, image embeddings are jointly aligned with both label and attribute-enhanced text embeddings, balancing discrimination for seen categories and transferability to unseen ones. Considering the availability of category exposure, our inference dynamically selects between standard label embeddings for seen categories and attribute-enhanced embeddings for unseen ones to ensure effective adaptation. Extensive experiments on 15 benchmark datasets demonstrate that SemPT achieves state-of-the-art performance across various settings, including base-to-novel generalization, cross-dataset transfer, cross-domain transfer, and few-shot learning.
Abstract (translated)
视觉领域的迁移学习在处理未见过的类别时，是一个活跃的研究领域但也是一个具有挑战性的任务。这是因为保留特定类别的表示与获取可转移知识之间存在着内在冲突。预先训练于大量图像-文本对上的视觉-语言模型（VLMs）提供了一个有希望的解决方案。然而，现有的提示微调方法依赖于稀疏的类别标签或由大型语言模型生成的不同描述，这些方法会分割知识表示并阻碍迁移能力。为了克服这一限制，我们引入了语义提示调整（SemPT），这是一种新的框架，通过利用跨类别的共享属性级知识来解决泛化挑战。 具体来说，SemPT采用了两步提示策略来引导大型语言模型提取共享的视觉属性，并生成属性级别的描述，在标签之外捕捉可转移的语义线索的同时确保结构的一致性。然后，对属性级别描述的嵌入应用基于图像指导的加权方法以减少无关属性带来的噪声并增强文本嵌入的质量。此外，图像嵌入同时与经过改进的文本嵌入（包括标签和属性改进两种）对齐，在区分已见类别和为未见过类别提供迁移能力之间保持平衡。 考虑到类别暴露的不同程度，我们的推断过程会动态选择在已见类别上使用标准标签嵌入而在未见过类别上采用属性增强的嵌入，以确保有效的适应性。在15个基准数据集上的广泛实验表明，SemPT在各种设置下达到了最先进的性能，包括基础到新颖的泛化、跨数据集迁移、跨域迁移和少量样本学习。
URL
https://arxiv.org/abs/2508.10645
PDF
-
A dataset and model for recognition of audiologically relevant environments for hearing aids: AHEAD-DS and YAMNet+
2025-08-14 05:59:21Henry Zhong, J\"org M. Buchholz, Julian Maclaren, Simon Carlile, Richard LyonAbstract
Scene recognition of audiologically relevant environments is important for hearing aids; however, it is challenging, in part because of the limitations of existing datasets. Datasets often lack public accessibility, completeness, or audiologically relevant labels, hindering systematic comparison of machine learning models. Deploying these models on resource-constrained edge devices presents another challenge. Our solution is two-fold: we leverage several open source datasets to create AHEAD-DS, a dataset designed for scene recognition of audiologically relevant environments, and introduce YAMNet+, a sound recognition model. AHEAD-DS aims to provide a standardised, publicly available dataset with consistent labels relevant to hearing aids, facilitating model comparison. YAMNet+ is designed for deployment on edge devices like smartphones connected to hearing devices, such as hearing aids and wireless earphones with hearing aid functionality; serving as a baseline model for sound-based scene recognition. YAMNet+ achieved a mean average precision of 0.83 and accuracy of 0.93 on the testing set of AHEAD-DS across fourteen categories of audiologically relevant environments. We found that applying transfer learning from the pretrained YAMNet model was essential. We demonstrated real-time sound-based scene recognition capabilities on edge devices by deploying YAMNet+ to an Android smartphone. Even with a Google Pixel 3 (a phone with modest specifications, released in 2018), the model processes audio with approximately 50ms of latency to load the model, and an approximate linear increase of 30ms per 1 second of audio. Our website and code this https URL .
Abstract (translated)
听力相关环境的场景识别对于助听设备来说非常重要，但由于现有数据集存在的一些限制（如缺乏公共访问性、完整性或与听力相关的标签），这方面的研究面临不少挑战。这些不足阻碍了机器学习模型之间的系统比较和评估。此外，在资源受限的边缘设备上部署这些模型也是一项挑战。 我们的解决方案分为两个部分：首先，我们利用几个开源数据集创建了一个名为AHEAD-DS的数据集，该数据集专为听力相关的环境场景识别设计，并且提供标准化、公开可用并带有与助听器相关的一致标签。其次，我们引入了YAMNet+模型，这是一种旨在部署在诸如智能手机等边缘设备上的声音识别模型，这些设备连接着如助听器和具备助听功能的无线耳机等装置，用作基于声音场景识别的基础模型。 AHEAD-DS数据集包含了十四类听力相关的环境类别，并为它们提供了标准标签，使得不同的机器学习模型能够进行有效比较。我们的YAMNet+模型在测试集上达到了平均精度（mean average precision）0.83和准确率（accuracy）0.93的成绩。 我们发现从预训练的YAMNet模型中应用迁移学习是十分必要的，并且我们在Android手机上部署了YAMNet+，展示了其实时声音场景识别的能力。即使是在2018年发布的Google Pixel 3这样的设备上（性能较为一般），该模型也能以大约50毫秒的时间加载并运行，并且每处理一秒钟的音频只增加了约30毫秒的时间。 我们的研究网站和代码可以在 [这里](#) 查看。（注意：原文中提供的网址被省略了，请您根据实际情况填写具体链接。）
URL
https://arxiv.org/abs/2508.10360
PDF
-
Explainable AI Technique in Lung Cancer Detection Using Convolutional Neural Networks
2025-08-13 21:02:38Nishan Rai, Sujan Khatri, Devendra RisalAbstract
Early detection of lung cancer is critical to improving survival outcomes. We present a deep learning framework for automated lung cancer screening from chest computed tomography (CT) images with integrated explainability. Using the IQ-OTH/NCCD dataset (1,197 scans across Normal, Benign, and Malignant classes), we evaluate a custom convolutional neural network (CNN) and three fine-tuned transfer learning backbones: DenseNet121, ResNet152, and VGG19. Models are trained with cost-sensitive learning to mitigate class imbalance and evaluated via accuracy, precision, recall, F1-score, and ROC-AUC. While ResNet152 achieved the highest accuracy (97.3%), DenseNet121 provided the best overall balance in precision, recall, and F1 (up to 92%, 90%, 91%, respectively). We further apply Shapley Additive Explanations (SHAP) to visualize evidence contributing to predictions, improving clinical transparency. Results indicate that CNN-based approaches augmented with explainability can provide fast, accurate, and interpretable support for lung cancer screening, particularly in resource-limited settings.
Abstract (translated)
早期检测肺癌对于改善生存结果至关重要。我们提出了一种深度学习框架，用于从胸部计算机断层扫描（CT）图像中自动筛查肺癌，并集成了可解释性功能。利用IQ-OTH/NCCD数据集（包括1,197个跨正常、良性、恶性类别的扫描），我们评估了一个定制的卷积神经网络（CNN）和三种经过微调的迁移学习骨干：DenseNet121、ResNet152和VGG19。模型通过成本敏感学习进行训练，以缓解类别不平衡，并通过准确率、精确度、召回率、F1分数和ROC-AUC指标进行评估。虽然ResNet152获得了最高的准确性（97.3%），但DenseNet121在精确度、召回率和F1得分方面提供了最佳的整体平衡（分别达到92%、90%、91%）。我们进一步应用Shapley Additive Explanations（SHAP）来可视化支持预测的证据，提高临床透明度。结果表明，结合可解释性的基于CNN的方法可以为肺癌筛查提供快速、准确且易于理解的支持，特别是在资源有限的情况下尤为有效。
URL
https://arxiv.org/abs/2508.10196
PDF
-
Improving watermelon disease classification with generative artificial intelligence -based synthetic and real-field images via a custom EfficientNetV2-L model
2025-08-13 19:39:39Nitin Rai, Nathan S. Boyd, Gary E. Vallad, Arnold W. SchumannAbstract
The current advancements in generative artificial intelligence (GenAI) models have paved the way for new possibilities for generating high-resolution synthetic images, thereby offering a promising alternative to traditional image acquisition for training computer vision models in agriculture. In the context of crop disease diagnosis, GenAI models are being used to create synthetic images of various diseases, potentially facilitating model creation and reducing the dependency on resource-intensive in-field data collection. However, limited research has been conducted on evaluating the effectiveness of integrating real with synthetic images to improve disease classification performance. Therefore, this study aims to investigate whether combining a limited number of real images with synthetic images can enhance the prediction accuracy of an EfficientNetV2-L model for classifying watermelon \textit{(Citrullus lanatus)} diseases. The training dataset was divided into five treatments: H0 (only real images), H1 (only synthetic images), H2 (1:1 real-to-synthetic), H3 (1:10 real-to-synthetic), and H4 (H3 + random images to improve variability and model generalization). All treatments were trained using a custom EfficientNetV2-L architecture with enhanced fine-tuning and transfer learning techniques. Models trained on H2, H3, and H4 treatments demonstrated high precision, recall, and F1-score metrics. Additionally, the weighted F1-score increased from 0.65 (on H0) to 1.00 (on H3-H4) signifying that the addition of a small number of real images with a considerable volume of synthetic images improved model performance and generalizability. Overall, this validates the findings that synthetic images alone cannot adequately substitute for real images; instead, both must be used in a hybrid manner to maximize model performance for crop disease classification.
Abstract (translated)
在生成式人工智能（GenAI）模型的最新进展推动下，高分辨率合成图像的生成已成为可能。这为农业中训练计算机视觉模型提供了传统图像获取方法之外的一个有前景的选择。特别是在作物病害诊断领域，GenAI 模型被用来创建各种疾病的合成图像，这有可能促进模型创建并减少对资源密集型实地数据收集的依赖。然而，关于将真实与合成图像相结合以提高疾病分类性能的有效性的研究却相对较少。 因此，本研究旨在调查使用少量的真实图像和大量合成图像结合是否可以提升EfficientNetV2-L模型在西瓜（Citrullus lanatus）病害分类上的预测精度。训练数据集被划分为五种处理方式：H0（仅真实图像）、H1（仅合成图像）、H2（真实与合成图像比例为1:1）、H3（真实与合成图像比例为1:10），以及H4（在H3基础上加入随机图像以提高多样性和模型泛化能力）。所有处理方式均使用增强的微调和迁移学习技术训练了自定义的EfficientNetV2-L架构。结果显示，采用H2、H3及H4处理方式训练出的模型具有高精度、召回率和F1评分等指标。另外，在这些处理下加权F1评分从0.65（仅使用真实图像时）提高到了1.00（在使用了少量的真实图像和大量合成图像的情况下），这表明，适量的真实图像与大量的合成图像是提升模型性能和泛化能力的关键。 总的来说，这项研究证明了单纯依靠合成图像无法充分替代真实图像；相反，两种方式的混合使用可以最大化地提高作物病害分类中的模型性能。
URL
https://arxiv.org/abs/2508.10156
PDF
-
From Source to Target: Leveraging Transfer Learning for Predictive Process Monitoring in Organizations
2025-08-11 15:03:50Sven Weinzierl, Sandra Zilker, Annina Liessmann, Martin K\"appel, Weixin Wang, Martin MatznerAbstract
Event logs reflect the behavior of business processes that are mapped in organizational information systems. Predictive process monitoring (PPM) transforms these data into value by creating process-related predictions that provide the insights required for proactive interventions at process runtime. Existing PPM techniques require sufficient amounts of event data or other relevant resources that might not be readily available, preventing some organizations from utilizing PPM. The transfer learning-based PPM technique presented in this paper allows organizations without suitable event data or other relevant resources to implement PPM for effective decision support. The technique is instantiated in two real-life use cases, based on which numerical experiments are performed using event logs for IT service management processes in an intra- and inter-organizational setting. The results of the experiments suggest that knowledge of one business process can be transferred to a similar business process in the same or a different organization to enable effective PPM in the target context. With the proposed technique, organizations can benefit from transfer learning in an intra- and inter-organizational setting, where resources like pre-trained models are transferred within and across organizational boundaries.
Abstract (translated)
事件日志反映了组织信息系统中映射的业务流程的行为。预测过程监控（PPM）通过将这些数据转化为与实时业务流程相关的预测，从而提供了价值，使组织能够进行主动干预以支持决策。现有的PPM技术通常需要大量的事件数据或其他相关资源，而这些资源在某些情况下可能并不容易获得，导致一些组织无法使用PPM。本文介绍的一种基于迁移学习的PPM技术允许没有合适事件数据或其它相关资源的组织也能实施有效的PPM，以支持其业务决策。 该技术通过两个现实用例得以具体应用，并且在此基础上利用信息技术服务管理过程中的事件日志，在组织内部和跨组织的不同场景下进行了数值实验。这些实验证明了一种业务流程的知识可以被转移到相似的其他业务流程中——无论是同一家公司还是不同的公司，从而在目标上下文中实现有效的PPM。 通过这种提议的技术，无论是在同一组织内部还是跨组织间，资源如预训练模型都可以进行转移利用，从而使各个组织能够从迁移学习中受益。
URL
https://arxiv.org/abs/2508.08061
PDF
-
Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification
2025-08-11 03:18:47Zhaorui Tan, Tan Pan, Kaizhu Huang, Weimiao Yu, Kai Yao, Chen Jiang, Qiufeng Wang, Anh Nguyen, Xin Guo, Yuan Cheng, Xi YangAbstract
LayerNorm is pivotal in Vision Transformers (ViTs), yet its fine-tuning dynamics under data scarcity and domain shifts remain underexplored. This paper shows that shifts in LayerNorm parameters after fine-tuning (LayerNorm shifts) are indicative of the transitions between source and target domains; its efficacy is contingent upon the degree to which the target training samples accurately represent the target domain, as quantified by our proposed Fine-tuning Shift Ratio ($FSR$). Building on this, we propose a simple yet effective rescaling mechanism using a scalar $\lambda$ that is negatively correlated to $FSR$ to align learned LayerNorm shifts with those ideal shifts achieved under fully representative data, combined with a cyclic framework that further enhances the LayerNorm fine-tuning. Extensive experiments across natural and pathological images, in both in-distribution (ID) and out-of-distribution (OOD) settings, and various target training sample regimes validate our framework. Notably, OOD tasks tend to yield lower $FSR$ and higher $\lambda$ in comparison to ID cases, especially with scarce data, indicating under-represented target training samples. Moreover, ViTFs fine-tuned on pathological data behave more like ID settings, favoring conservative LayerNorm updates. Our findings illuminate the underexplored dynamics of LayerNorm in transfer learning and provide practical strategies for LayerNorm fine-tuning.
Abstract (translated)
层归一化（LayerNorm）在视觉变换器（ViT）中起着至关重要的作用，但其在数据稀缺和领域变化情况下的微调动态特性尚未得到充分研究。本文表明，在微调后出现的层归一化参数的变化（即“层归一化偏移”）可以指示源域与目标域之间的转换；它的有效性取决于目标训练样本多大程度上准确代表了目标域，这可以通过我们提出的微调偏移比率($FSR$)来量化。基于此发现，本文提出了一种简单而有效的重缩放机制，该机制使用一个标量$\lambda$（与$FSR$负相关）来对齐学习到的层归一化偏移和完全代表性的数据下理想化的层归一化偏移，并结合了一个循环框架以进一步增强层归一化的微调过程。在自然和病理图像上进行广泛的跨分布（ID）和非分布（OOD）设置以及各种目标训练样本制度下的实验验证了我们的框架的有效性。 值得注意的是，与ID情况相比，特别是在数据稀缺的情况下，OOD任务往往导致较低的$FSR$值和较高的$\lambda$值，这表明了目标训练样本代表性不足。此外，在病理数据上微调后的ViT表现出更接近于ID设置的行为，并倾向于保守地更新层归一化参数。我们的研究揭示了层归一化在迁移学习中被忽视的动力学特性，并为层归一化的微调提供了实用策略。
URL
https://arxiv.org/abs/2508.07577
PDF
-
CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
2025-08-10 11:09:41Yexing Du, Kaiyuan Liu, Youcheng Pan, Zheng Chu, Bo Yang, Xiaocheng Feng, Yang Xiang, Ming LiuAbstract
As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. However, existing benchmarks for evaluating the reliability of Multimodal Large Language Models (MLLMs) predominantly focus on textual or visual modalities with a primary emphasis on English, which creates a gap in evaluation when processing multilingual input, especially in speech. To bridge this gap, we propose a novel \textbf{C}ross-lingual and \textbf{C}ross-modal \textbf{F}actuality benchmark (\textbf{CCFQA}). Specifically, the CCFQA benchmark contains parallel speech-text factual questions across 8 languages, designed to systematically evaluate MLLMs' cross-lingual and cross-modal factuality capabilities. Our experimental results demonstrate that current MLLMs still face substantial challenges on the CCFQA benchmark. Furthermore, we propose a few-shot transfer learning strategy that effectively transfers the Question Answering (QA) capabilities of LLMs in English to multilingual Spoken Question Answering (SQA) tasks, achieving competitive performance with GPT-4o-mini-Audio using just 5-shot training. We release CCFQA as a foundational research resource to promote the development of MLLMs with more robust and reliable speech understanding capabilities. Our code and dataset are available at this https URL.
Abstract (translated)
随着大型语言模型（LLM）在多语言世界中越来越受欢迎，确保无幻觉的事实性变得尤为重要。然而，目前评估多模态大型语言模型（MLLMs）可靠性的现有基准主要集中在文本或视觉模式上，并且以英语为主，这在处理多种语言的输入时，尤其是语音输入时，造成了评估上的缺口。为弥补这一差距，我们提出了一种新颖的跨语言和跨模态事实性基准测试（CCFQA）。具体来说，CCFQA 基准包含了跨越8种语言的平行语音-文本事实问题，旨在系统地评估MLLMs在跨语言和跨模态方面的事实能力。我们的实验结果表明，当前的MLLMs 在CCFQA基准测试中仍面临重大挑战。此外，我们还提出了一种基于少量样本的学习策略，可以有效地将英语环境中大型语言模型（LLM）的问题回答（QA）能力转移到多语言口语问答（SQA）任务上，并且仅通过5次训练就能达到与GPT-4o-mini-Audio相当的性能水平。我们将CCFQA作为基础研究资源发布，以促进具有更强大和可靠语音理解能力的MLLMs的发展。我们的代码和数据集可在[此链接](https://this-url.com/)获取。
URL
https://arxiv.org/abs/2508.07295
PDF
-
Can Diffusion Models Bridge the Domain Gap in Cardiac MR Imaging?
2025-08-08 13:57:48Xin Ci Wong, Duygu Sarikaya, Kieran Zucker, Marc De Kamps, Nishant RavikumarAbstract
Magnetic resonance (MR) imaging, including cardiac MR, is prone to domain shift due to variations in imaging devices and acquisition protocols. This challenge limits the deployment of trained AI models in real-world scenarios, where performance degrades on unseen domains. Traditional solutions involve increasing the size of the dataset through ad-hoc image augmentation or additional online training/transfer learning, which have several limitations. Synthetic data offers a promising alternative, but anatomical/structural consistency constraints limit the effectiveness of generative models in creating image-label pairs. To address this, we propose a diffusion model (DM) trained on a source domain that generates synthetic cardiac MR images that resemble a given reference. The synthetic data maintains spatial and structural fidelity, ensuring similarity to the source domain and compatibility with the segmentation mask. We assess the utility of our generative approach in multi-centre cardiac MR segmentation, using the 2D nnU-Net, 3D nnU-Net and vanilla U-Net segmentation networks. We explore domain generalisation, where, domain-invariant segmentation models are trained on synthetic source domain data, and domain adaptation, where, we shift target domain data towards the source domain using the DM. Both strategies significantly improved segmentation performance on data from an unseen target domain, in terms of surface-based metrics (Welch's t-test, p < 0.01), compared to training segmentation models on real data alone. The proposed method ameliorates the need for transfer learning or online training to address domain shift challenges in cardiac MR image analysis, especially useful in data-scarce settings.
Abstract (translated)
磁共振（MR）成像，包括心脏MR成像，在不同的成像设备和采集协议下容易发生领域偏移。这种挑战限制了训练好的AI模型在实际应用场景中的部署，因为它们在未见过的数据域上的性能会下降。传统的解决方案是通过人工图像增强或额外的在线训练/迁移学习来扩大数据集规模，但这几种方法存在一些局限性。合成数据为解决这一问题提供了一种有希望的替代方案，但由于解剖结构一致性约束的存在，生成模型在创建影像-标签对时的有效性受到了限制。 为了应对这些问题，我们提出了一种基于扩散模型（DM）的方法，该模型在一个源领域上进行训练，并能够根据给定的参考图像产生类似的心脏MR合成图像。这种方法产生的数据保持了空间和结构的一致性，确保与原数据域相似且与分割掩模兼容。我们在多中心心脏MR分割任务中评估了我们生成方法的有效性，使用了2D nnU-Net、3D nnU-Net以及普通的U-Net分割网络。 我们的研究探索了两种策略：领域泛化和领域适应。在领域泛化中，我们将不变的分割模型训练于合成源域数据上；而在领域适应中，我们利用扩散模型将目标域数据向源域转换。这两种方法均显著提高了对未见目标域数据的分割性能（基于Welch's t-test, p < 0.01）。与仅在真实数据上训练分割模型相比，这些策略在表面度量指标方面表现出明显优势。 所提出的这种方法改善了处理心脏MR图像分析中的领域偏移问题的需求，特别是在数据匮乏的情况下，减少了迁移学习或在线培训的必要性。
URL
https://arxiv.org/abs/2508.06327
PDF
-
Textual Inversion for Efficient Adaptation of Open-Vocabulary Object Detectors Without Forgetting
2025-08-07 12:28:08Frank Ruis, Gertjan Burghouts, Hugo KuijfAbstract
Recent progress in large pre-trained vision language models (VLMs) has reached state-of-the-art performance on several object detection benchmarks and boasts strong zero-shot capabilities, but for optimal performance on specific targets some form of finetuning is still necessary. While the initial VLM weights allow for great few-shot transfer learning, this usually involves the loss of the original natural language querying and zero-shot capabilities. Inspired by the success of Textual Inversion (TI) in personalizing text-to-image diffusion models, we propose a similar formulation for open-vocabulary object detection. TI allows extending the VLM vocabulary by learning new or improving existing tokens to accurately detect novel or fine-grained objects from as little as three examples. The learned tokens are completely compatible with the original VLM weights while keeping them frozen, retaining the original model's benchmark performance, and leveraging its existing capabilities such as zero-shot domain transfer (e.g., detecting a sketch of an object after training only on real photos). The storage and gradient calculations are limited to the token embedding dimension, requiring significantly less compute than full-model fine-tuning. We evaluated whether the method matches or outperforms the baseline methods that suffer from forgetting in a wide variety of quantitative and qualitative experiments.
Abstract (translated)
近期，在大型预训练视觉语言模型（VLMs）方面取得的进展已经在多个目标检测基准测试中达到了最先进的性能，并且具备强大的零样本能力，但为了在特定任务上达到最佳效果，仍需要某种形式的微调。虽然最初的VLM权重允许进行出色的少量样例迁移学习，但这通常会导致丧失原始的自然语言查询能力和零样本能力。 受Textual Inversion（TI）成功个性化文本到图像扩散模型的启发，我们提出了一种类似的开放词汇目标检测方法。TI通过从最少三个示例中学习新或改进现有标记来扩展VLM词汇表，以准确检测新颖或细粒度的对象。所学得的标记与原始VLM权重完全兼容，并且保持这些权重不变，同时保留模型在基准测试中的性能和现有的能力，例如零样本领域转移（即，在仅使用真实照片进行训练后识别物体素描）。存储和梯度计算仅限于标记嵌入维度，所需计算量远少于全模型微调。 我们在广泛的定量和定性实验中评估了该方法是否能与那些因遗忘问题而表现不佳的基线方法相匹配或超越。
URL
https://arxiv.org/abs/2508.05323
PDF
-
Segmenting the Complex and Irregular in Two-Phase Flows: A Real-World Empirical Study with SAM2
2025-08-07 10:17:46Semanur K\"u\c{c}\"uk, Cosimo Della Santina, Angeliki LaskariAbstract
Segmenting gas bubbles in multiphase flows is a critical yet unsolved challenge in numerous industrial settings, from metallurgical processing to maritime drag reduction. Traditional approaches-and most recent learning-based methods-assume near-spherical shapes, limiting their effectiveness in regimes where bubbles undergo deformation, coalescence, or breakup. This complexity is particularly evident in air lubrication systems, where coalesced bubbles form amorphous and topologically diverse patches. In this work, we revisit the problem through the lens of modern vision foundation models. We cast the task as a transfer learning problem and demonstrate, for the first time, that a fine-tuned Segment Anything Model SAM v2.1 can accurately segment highly non-convex, irregular bubble structures using as few as 100 annotated images.
Abstract (translated)
在多相流中的气泡分割是许多工业环境中的一个关键但尚未解决的挑战，从冶金加工到减少海洋阻力。传统方法和最近基于学习的方法都假设气泡形状接近球形，这限制了它们在气泡发生变形、合并或破裂的情况下的有效性。这种复杂性尤其体现在空气润滑系统中，在那里合并后的气泡形成了无定形且拓扑多样的区域。 在这项工作中，我们通过现代视觉基础模型的视角重新审视这个问题。我们将任务视为一个迁移学习问题，并首次证明，通过对Segment Anything Model（SAM）v2.1进行微调，可以仅使用100张标注图像准确地分割出高度非凸和不规则形状的气泡结构。 这段话强调了在多相流中气泡复杂几何形态所带来的挑战，并介绍了如何利用现代视觉基础模型及迁移学习技术来有效解决这一问题。
URL
https://arxiv.org/abs/2508.05227
PDF
-
Perch 2.0: The Bittern Lesson for Bioacoustics
2025-08-06 17:34:43Bart van Merri\"enboer, Vincent Dumoulin, Jenny Hamer, Lauren Harrell, Andrea Burns, Tom DentonAbstract
Perch is a performant pre-trained model for bioacoustics. It was trained in supervised fashion, providing both off-the-shelf classification scores for thousands of vocalizing species as well as strong embeddings for transfer learning. In this new release, Perch 2.0, we expand from training exclusively on avian species to a large multi-taxa dataset. The model is trained with self-distillation using a prototype-learning classifier as well as a new source-prediction training criterion. Perch 2.0 obtains state-of-the-art performance on the BirdSet and BEANS benchmarks. It also outperforms specialized marine models on marine transfer learning tasks, despite having almost no marine training data. We present hypotheses as to why fine-grained species classification is a particularly robust pre-training task for bioacoustics.
Abstract (translated)
Perch 是一个高性能的预训练模型，专门用于生物声学领域。它采用监督学习方式训练而成，能够提供数千种发声物种的现成分类得分以及强大的迁移学习嵌入表示。在本次新发布的 Perch 2.0 中，我们从仅对鸟类物种进行专有训练扩展到了一个包含大量多分类群（multi-taxa）数据集的训练。Perch 2.0 使用自蒸馏技术和原型学习分类器，并引入了一种新的源预测训练准则来进一步优化模型性能。 在 BirdSet 和 BEANS 这两个基准测试中，Perch 2.0 达到了最先进的性能水平。尽管其几乎没有任何海洋数据的训练经验，但在海洋生物声学迁移学习任务上仍能超越专门针对海洋物种设计的预训练模型的表现。我们还提出了假设来解释为什么细粒度物种分类是一个特别稳健且有效的生物声学领域中的预训练任务。
URL
https://arxiv.org/abs/2508.04665
PDF
-
Transferring Expert Cognitive Models to Social Robots via Agentic Concept Bottleneck Models
2025-08-06 01:24:06Xinyu Zhao, Zhen Tan, Maya Enisman, Minjae Seo, Marta R. Durantini, Dolores Albarracin, Tianlong ChenAbstract
Successful group meetings, such as those implemented in group behavioral-change programs, work meetings, and other social contexts, must promote individual goal setting and execution while strengthening the social relationships within the group. Consequently, an ideal facilitator must be sensitive to the subtle dynamics of disengagement, difficulties with individual goal setting and execution, and interpersonal difficulties that signal a need for intervention. The challenges and cognitive load experienced by facilitators create a critical gap for an embodied technology that can interpret social exchanges while remaining aware of the needs of the individuals in the group and providing transparent recommendations that go beyond powerful but "black box" foundation models (FMs) that identify social cues. We address this important demand with a social robot co-facilitator that analyzes multimodal meeting data and provides discreet cues to the facilitator. The robot's reasoning is powered by an agentic concept bottleneck model (CBM), which makes decisions based on human-interpretable concepts like participant engagement and sentiments, ensuring transparency and trustworthiness. Our core contribution is a transfer learning framework that distills the broad social understanding of an FM into our specialized and transparent CBM. This concept-driven system significantly outperforms direct zero-shot FMs in predicting the need for intervention and enables real-time human correction of its reasoning. Critically, we demonstrate robust knowledge transfer: the model generalizes across different groups and successfully transfers the expertise of senior human facilitators to improve the performance of novices. By transferring an expert's cognitive model into an interpretable robotic partner, our work provides a powerful blueprint for augmenting human capabilities in complex social domains.
Abstract (translated)
成功的团队会议，例如在行为改变项目、工作会议和其他社交场合中实施的那些，必须促进个人目标设定和执行的同时加强团队内部的社会关系。因此，理想的主持人需要对参与者参与度下降、个人目标设定和执行困难以及人际问题等微妙动态保持敏感，这些信号表明需要介入。主持人面临的挑战和认知负荷为一种能够解读社会互动并关注群体成员需求的实体技术创造了一个关键缺口，这种技术可以提供超越强大但像“黑盒”一样的基础模型（FMs）所识别的社会线索的透明建议。 我们通过一个社交机器人共主持人来应对这一重要需求。该机器人分析多模式会议数据，并向主持人提供隐性提示。机器人的推理由代理概念瓶颈模型（CBM）驱动，基于参与者参与度和情感等人类可解释的概念进行决策，确保其透明性和可靠性。我们的核心贡献是一个迁移学习框架，它将基础模型的广泛社交理解提炼成我们专有的、透明的CBM。 这一概念驱动系统在预测介入需求方面显著优于直接零样本基础模型，并且能够实现实时的人类对其推理进行修正。尤为重要的是，我们证明了强大的知识转移：该模型可以在不同的团队之间推广并成功地将资深人类主持人的专业知识转移到新手身上以提高其表现。通过将专家的认知模型转化为一个可解释的机器人伙伴，我们的工作为在复杂社交领域增强人类能力提供了一个强有力的蓝图。
URL
https://arxiv.org/abs/2508.03998
PDF
-
Investigating the Impact of Large-Scale Pre-training on Nutritional Content Estimation from 2D Images
2025-08-06 00:57:55Michele Andrade, Guilherme A. L. Silva, Val\'eria Santos, Gladston Moreira, Eduardo LuzAbstract
Estimating the nutritional content of food from images is a critical task with significant implications for health and dietary monitoring. This is challenging, especially when relying solely on 2D images, due to the variability in food presentation, lighting, and the inherent difficulty in inferring volume and mass without depth information. Furthermore, reproducibility in this domain is hampered by the reliance of state-of-the-art methods on proprietary datasets for large-scale pre-training. In this paper, we investigate the impact of large-scale pre-training datasets on the performance of deep learning models for nutritional estimation using only 2D images. We fine-tune and evaluate Vision Transformer (ViT) models pre-trained on two large public datasets, ImageNet and COYO, comparing their performance against baseline CNN models (InceptionV2 and ResNet-50) and a state-of-the-art method pre-trained on the proprietary JFT-300M dataset. We conduct extensive experiments on the Nutrition5k dataset, a large-scale collection of real-world food plates with high-precision nutritional annotations. Our evaluation using Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAE%) reveals that models pre-trained on JFT-300M significantly outperform those pre-trained on public datasets. Unexpectedly, the model pre-trained on the massive COYO dataset performs worse than the model pre-trained on ImageNet for this specific regression task, refuting our initial hypothesis. Our analysis provides quantitative evidence highlighting the critical role of pre-training dataset characteristics, including scale, domain relevance, and curation quality, for effective transfer learning in 2D nutritional estimation.
Abstract (translated)
从图像估计食物的营养成分是一项具有重要健康和饮食监测意义的关键任务。然而，仅依赖二维图像来完成这一任务极具挑战性，因为食物呈现方式、光线条件的变化以及缺乏深度信息使得推断体积和质量变得困难。此外，最先进的方法严重依赖专有数据集进行大规模预训练，这在很大程度上阻碍了该领域的可重复性。 在这篇论文中，我们研究了大规模预训练数据集对仅使用二维图像进行营养估计的深层学习模型性能的影响。我们将经过ImageNet和COYO两个大型公共数据集预训练的Vision Transformer（ViT）模型进行微调，并对其与基线CNN模型（InceptionV2和ResNet-50）以及在专有JFT-300M数据集上进行了大规模预训练的方法进行比较。我们在Nutrition5k数据集上进行了广泛的实验，这是一个包含大量现实世界食物照片的数据集，这些照片具有高精度的营养成分注释。我们的评估结果显示，在使用均方绝对误差（MAE）和平均绝对百分比误差（MAPE）作为评价指标时，预训练于JFT-300M数据集上的模型显著优于基于公共数据集预训练的模型。令人意外的是，大规模COYO数据集上预训练的模型在此特定回归任务中的表现不如在ImageNet上进行预训练的模型，这反驳了我们的初始假设。 我们分析提供了定量证据，强调了预训练数据集特征——包括规模、相关领域和整理质量对于二维营养估计中有效的迁移学习至关重要。
URL
https://arxiv.org/abs/2508.03996
PDF
-
Active Learning and Transfer Learning for Anomaly Detection in Time-Series Data
2025-08-05 21:30:41John D. Kelleher, Matthew Nicholson, Rahul Agrahari, Clare ConranAbstract
This paper examines the effectiveness of combining active learning and transfer learning for anomaly detection in cross-domain time-series data. Our results indicate that there is an interaction between clustering and active learning and in general the best performance is achieved using a single cluster (in other words when clustering is not applied). Also, we find that adding new samples to the training set using active learning does improve model performance but that in general, the rate of improvement is slower than the results reported in the literature suggest. We attribute this difference to an improved experimental design where distinct data samples are used for the sampling and testing pools. Finally, we assess the ceiling performance of transfer learning in combination with active learning across several datasets and find that performance does initially improve but eventually begins to tail off as more target points are selected for inclusion in training. This tail-off in performance may indicate that the active learning process is doing a good job of sequencing data points for selection, pushing the less useful points towards the end of the selection process and that this tail-off occurs when these less useful points are eventually added. Taken together our results indicate that active learning is effective but that the improvement in model performance follows a linear flat function concerning the number of points selected and labelled.
Abstract (translated)
本文研究了在跨域时间序列数据异常检测中结合主动学习和迁移学习的有效性。我们的结果显示，聚类与主动学习之间存在相互作用，并且总体而言，在不应用聚类的情况下（即使用单个簇时）可以获得最佳性能。此外，我们发现通过主动学习向训练集添加新样本确实可以提高模型的性能，但通常改善的速度比文献报道的结果要慢。我们认为这种差异是由于改进了实验设计，其中用于采样和测试的数据样本是不同的。 最后，我们在多个数据集中评估了迁移学习与主动学习相结合时的天花板性能，并发现其初始性能有所提升，但在选择更多目标点进行训练后，性能最终开始下降。这种性能下降可能表明，主动学习过程很好地为选定点进行了排序，将不太有用的点推到了选择过程的末尾，而当这些不太有用的点被加入到训练集中时，便出现了这一现象。 综合来看，我们的结果表明，主动学习是有效的，但模型性能的提升与所选取和标记的数据点数量之间的关系遵循一种线性且渐进的函数。
URL
https://arxiv.org/abs/2508.03921
PDF
-
evTransFER: A Transfer Learning Framework for Event-based Facial Expression Recognition
2025-08-05 16:26:09Rodrigo Verschae, Ignacio Bugueno-CordovaAbstract
Event-based cameras are bio-inspired vision sensors that asynchronously capture per-pixel intensity changes with microsecond latency, high temporal resolution, and high dynamic range, providing valuable information about the spatio-temporal dynamics of the scene. In the present work, we propose evTransFER, a transfer learning-based framework and architecture for face expression recognition using event-based cameras. The main contribution is a feature extractor designed to encode the spatio-temporal dynamics of faces, built by training an adversarial generative method on a different problem (facial reconstruction) and then transferring the trained encoder weights to the face expression recognition system. We show that this proposed transfer learning method greatly improves the ability to recognize facial expressions compared to training a network from scratch. In addition, we propose an architecture that incorporates an LSTM to capture longer-term facial expression dynamics, and we introduce a new event-based representation, referred to as TIE, both of which further improve the results. We evaluate the proposed framework on the event-based facial expression database e-CK+ and compare it to state-of-the-art methods. The results show that the proposed framework evTransFER achieves a 93.6\% recognition rate on the e-CK+ database, significantly improving the accuracy (25.9\% points or more) when compared to state-of-the-art performance for similar problems.
Abstract (translated)
基于事件的相机是受生物启发的视觉传感器，能够异步捕获像素级别的强度变化，并具有微秒级延迟、高时间分辨率和大动态范围的特点，为场景的空间-时间动力学提供了有价值的信息。在当前的工作中，我们提出了evTransFER框架与架构，用于基于事件的摄像机的人脸表情识别，采用了基于迁移学习的方法。主要贡献是一个特征提取器的设计，该设计能够编码人脸的空间-时间动态特性，通过在一个不同的问题（面部重建）上训练一种对抗性生成方法，并将训练好的编码器权重转移到人脸识别系统中来实现这一目标。我们展示了这种方法与从头开始训练网络相比，在识别面部表情的能力上有显著提升。 此外，还提出了一种结合LSTM的架构以捕捉更长期的人脸表情动态，并引入了一个新的基于事件表示的形式——TIE（Time-Indexed Event），这两种方法进一步提高了结果。我们在基于事件的表情数据库e-CK+上评估了所提出的框架，并将其与最先进的方法进行了比较。结果显示，我们的框架evTransFER在e-CK+数据库上的识别率达到93.6%，相较于同类问题中的最佳性能，在准确率上有显著的提高（25.9个百分点或更多）。
URL
https://arxiv.org/abs/2508.03609
PDF
-
Transfer Learning with EfficientNet for Accurate Leukemia Cell Classification
Abstract
Accurate classification of Acute Lymphoblastic Leukemia (ALL) from peripheral blood smear images is essential for early diagnosis and effective treatment planning. This study investigates the use of transfer learning with pretrained convolutional neural networks (CNNs) to improve diagnostic performance. To address the class imbalance in the dataset of 3,631 Hematologic and 7,644 ALL images, we applied extensive data augmentation techniques to create a balanced training set of 10,000 images per class. We evaluated several models, including ResNet50, ResNet101, and EfficientNet variants B0, B1, and B3. EfficientNet-B3 achieved the best results, with an F1-score of 94.30%, accuracy of 92.02%, andAUCof94.79%,outperformingpreviouslyreported methods in the C-NMCChallenge. Thesefindings demonstrate the effectiveness of combining data augmentation with advanced transfer learning models, particularly EfficientNet-B3, in developing accurate and robust diagnostic tools for hematologic malignancy detection.
Abstract (translated)
急性淋巴细胞白血病（ALL）的准确分类对于早期诊断和有效治疗计划至关重要。本研究探讨了使用预训练卷积神经网络（CNN）进行迁移学习以提高诊断性能的方法。为了应对包含3,631张血液学图像和7,644张ALL图像的数据集中类别不平衡的问题，我们应用了大量的数据增强技术，创建了一个每类包含10,000张图像的平衡训练集。我们评估了几种模型，包括ResNet50、ResNet101以及EfficientNet变体B0、B1和B3。其中，EfficientNet-B3表现最佳，其F1得分为94.30%，准确率为92.02%，AUC为94.79%，优于C-NMC挑战赛中之前报道的方法。这些发现证明了结合数据增强与高级迁移学习模型（尤其是EfficientNet-B3）在开发准确且鲁棒的血液恶性肿瘤检测工具方面的有效性。
URL
https://arxiv.org/abs/2508.06535
PDF
-
LoRA-based methods on Unet for transfer learning in Subarachnoid Hematoma Segmentation
2025-08-03 14:12:42Cristian Minoccheri, Matthew Hodgman, Haoyuan Ma, Rameez Merchant, Emily Wittrup, Craig Williamson, Kayvan NajarianAbstract
Aneurysmal subarachnoid hemorrhage (SAH) is a life-threatening neurological emergency with mortality rates exceeding 30%. Transfer learning from related hematoma types represents a potentially valuable but underexplored approach. Although Unet architectures remain the gold standard for medical image segmentation due to their effectiveness on limited datasets, Low-Rank Adaptation (LoRA) methods for parameter-efficient transfer learning have been rarely applied to convolutional neural networks in medical imaging contexts. We implemented a Unet architecture pre-trained on computed tomography scans from 124 traumatic brain injury patients across multiple institutions, then fine-tuned on 30 aneurysmal SAH patients from the University of Michigan Health System using 3-fold cross-validation. We developed a novel CP-LoRA method based on tensor CP-decomposition and introduced DoRA variants (DoRA-C, convDoRA, CP-DoRA) that decompose weight matrices into magnitude and directional components. We compared these approaches against existing LoRA methods (LoRA-C, convLoRA) and standard fine-tuning strategies across different modules on a multi-view Unet model. LoRA-based methods consistently outperformed standard Unet fine-tuning. Performance varied by hemorrhage volume, with all methods showing improved accuracy for larger volumes. CP-LoRA achieved comparable performance to existing methods while using significantly fewer parameters. Over-parameterization with higher ranks consistently yielded better performance than strictly low-rank adaptations. This study demonstrates that transfer learning between hematoma types is feasible and that LoRA-based methods significantly outperform conventional Unet fine-tuning for aneurysmal SAH segmentation.
Abstract (translated)
动脉瘤性蛛网膜下腔出血（SAH）是一种危及生命的神经紧急情况，死亡率超过30%。从相关血肿类型中进行迁移学习代表了一种潜在但尚未充分探索的方法。尽管Unet架构由于在有限数据集上的有效性而仍然是医学图像分割的金标准，但在医学成像上下文中，用于参数高效迁移学习的低秩适应（LoRA）方法却很少被应用到卷积神经网络上。我们基于来自124名创伤性脑损伤患者的计算机断层扫描图像进行预训练，并在密歇根大学医疗系统的30例动脉瘤性SAH患者数据集上使用三折交叉验证进行了微调。 我们开发了一种新的CP-LoRA方法，该方法基于张量CP分解，并引入了DoRA变体（DoRA-C、convDoRA和CP-DoRA），这些变体将权重矩阵分解为幅度和方向成分。我们在一个多视图Unet模型的不同模块上比较了这些方法与现有LoRA方法（LoRA-C、convLoRA）以及标准微调策略的性能。 基于LoRA的方法始终优于标准Unet微调方法。性能根据出血体积而变化，所有方法对于较大体积都显示出更高的准确性。CP-LoRA在使用显著较少参数的情况下达到了与现有方法相当的表现。使用更高秩进行过参数化总是比严格低秩适应表现出更好的性能。 本研究证明了血肿类型之间的迁移学习是可行的，并且基于LoRA的方法在动脉瘤性SAH分割中明显优于传统的Unet微调方法。
URL
https://arxiv.org/abs/2508.01772
PDF
-
Predicting EGFR Mutation in LUAD from Histopathological Whole-Slide Images Using Pretrained Foundation Model and Transfer Learning: An Indian Cohort Study
2025-08-02 12:57:16Sagar Singh Gwal, Rajan, Suyash Devgan, Shraddhanjali Satapathy, Abhishek Goyal, Nuruddin Mohammad Iqbal, Vivaan Jain, Prabhat Singh Mallik, Deepali Jain, Ishaan GuptaAbstract
Lung adenocarcinoma (LUAD) is a subtype of non-small cell lung cancer (NSCLC). LUAD with mutation in the EGFR gene accounts for approximately 46% of LUAD cases. Patients carrying EGFR mutations can be treated with specific tyrosine kinase inhibitors (TKIs). Hence, predicting EGFR mutation status can help in clinical decision making. H&E-stained whole slide imaging (WSI) is a routinely performed screening procedure for cancer staging and subtyping, especially affecting the Southeast Asian populations with significantly higher incidence of the mutation when compared to Caucasians (39-64% vs 7-22%). Recent progress in AI models has shown promising results in cancer detection and classification. In this study, we propose a deep learning (DL) framework built on vision transformers (ViT) based pathology foundation model and attention-based multiple instance learning (ABMIL) architecture to predict EGFR mutation status from H&E WSI. The developed pipeline was trained using data from an Indian cohort (170 WSI) and evaluated across two independent datasets: Internal test (30 WSI from Indian cohort) set, and an external test set from TCGA (86 WSI). The model shows consistent performance across both datasets, with AUCs of 0.933 (+/-0.010), and 0.965 (+/-0.015) for the internal and external test sets respectively. This proposed framework can be efficiently trained on small datasets, achieving superior performance as compared to several prior studies irrespective of training domain. The current study demonstrates the feasibility of accurately predicting EGFR mutation status using routine pathology slides, particularly in resource-limited settings using foundation models and attention-based multiple instance learning.
Abstract (translated)
肺腺癌（LUAD）是非小细胞肺癌（NSCLC）的一种亚型。在 LUAD 中，EGFR 基因突变约占 46% 的病例。携带 EGFR 突变的患者可以接受特定酪氨酸激酶抑制剂（TKIs）治疗。因此，预测 EGFR 突变状态有助于临床决策制定。HE 染色全切片成像 (WSI) 是癌症分期和分型的一种常规筛查方法，在东南亚人群中尤为适用，因为该地区的突变发病率显著高于高加索人种（39-64% 对比 7-22%）。近期人工智能模型的进步在癌症检测和分类方面取得了令人鼓舞的结果。在这项研究中，我们提出了一种基于视觉变压器 (ViT) 的病理学基础模型和注意力机制的多重实例学习 (ABMIL) 架构构建的深度学习（DL）框架，旨在从 HE WSI 中预测 EGFR 突变状态。该开发流程利用了来自印度队列的数据进行训练（170 张 WSI），并在两个独立数据集上进行了评估：内部测试集（30 张 WSI 来自印度队列）和外部测试集（TCGA 数据集中的 86 张 WSI）。该模型在两个数据集中表现出一致的性能，内部测试集和外部测试集分别获得了 AUC 分数为 0.933 (+/-0.010) 和 0.965 (+/-0.015)。此框架能够在较小的数据集上高效训练，并且无论训练领域如何，其表现均优于先前的多项研究。本研究表明，在资源有限的情况下使用基础模型和注意力机制多重实例学习可以准确预测 EGFR 突变状态，尤其适用于常规病理学切片的应用。
URL
https://arxiv.org/abs/2508.01352
PDF
