Contour
-
MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances
2025-09-21 16:14:51Junhyeok Lee, Helin Wang, Yaohan Guan, Thomas Thebaud, Laureano Moro-Velazquez, Jes\'us Villalba, Najim DehakAbstract
We introduce MaskVCT, a zero-shot voice conversion (VC) model that offers multi-factor controllability through multiple classifier-free guidances (CFGs). While previous VC models rely on a fixed conditioning scheme, MaskVCT integrates diverse conditions in a single model. To further enhance robustness and control, the model can leverage continuous or quantized linguistic features to enhance intellgibility and speaker similarity, and can use or omit pitch contour to control prosody. These choices allow users to seamlessly balance speaker identity, linguistic content, and prosodic factors in a zero-shot VC setting. Extensive experiments demonstrate that MaskVCT achieves the best target speaker and accent similarities while obtaining competitive word and character error rates compared to existing baselines. Audio samples are available at this https URL.
Abstract (translated)
我们介绍了MaskVCT，这是一种零样本语音转换（VC）模型，通过多种无分类器引导（CFGs）提供多因素可控性。与以往的VC模型依赖固定条件方案不同，MaskVCT在一个单一模型中整合了多样化的条件。为了进一步增强鲁棒性和控制能力，该模型可以利用连续或量化语言特征来提升可理解性和说话人相似度，并可以选择使用或忽略音高轮廓以控制语调。这些选择使用户能够在零样本VC环境中无缝平衡说话人身份、语言内容和语调因素。广泛的实验表明，MaskVCT在目标说话人的相似度和口音相似度方面表现最佳，在与现有基准相比时获得了具有竞争力的词错误率和字符错误率。音频样例可在[此链接](https://example.com)获取。（请注意，实际的URL应该替换为提供音频样本的具体链接）
URL
https://arxiv.org/abs/2509.17143
PDF
-
Uncertainty-Gated Deformable Network for Breast Tumor Segmentation in MR Images
2025-09-19 08:37:33Yue Zhang, Jiahua Dong, Chengtao Peng, Qiuli Wang, Dan Song, Guiduo DuanAbstract
Accurate segmentation of breast tumors in magnetic resonance images (MRI) is essential for breast cancer diagnosis, yet existing methods face challenges in capturing irregular tumor shapes and effectively integrating local and global features. To address these limitations, we propose an uncertainty-gated deformable network to leverage the complementary information from CNN and Transformers. Specifically, we incorporates deformable feature modeling into both convolution and attention modules, enabling adaptive receptive fields for irregular tumor contours. We also design an Uncertainty-Gated Enhancing Module (U-GEM) to selectively exchange complementary features between CNN and Transformer based on pixel-wise uncertainty, enhancing both local and global representations. Additionally, a Boundary-sensitive Deep Supervision Loss is introduced to further improve tumor boundary delineation. Comprehensive experiments on two clinical breast MRI datasets demonstrate that our method achieves superior segmentation performance compared with state-of-the-art methods, highlighting its clinical potential for accurate breast tumor delineation.
Abstract (translated)
在磁共振成像（MRI）中精确分割乳腺肿瘤对于乳腺癌的诊断至关重要，然而现有的方法在捕捉不规则肿瘤形状和有效整合局部与全局特征方面面临挑战。为了解决这些限制，我们提出了一种不确定性门控可变形网络，该网络利用了卷积神经网络（CNN）和变换器模型所携带的信息优势。具体来说，我们将可变形特征建模融入到卷积模块和注意力模块中，使网络能够根据不规则肿瘤轮廓自适应地调整感受野范围。此外，我们设计了一种不确定性门控增强模块（U-GEM），该模块能够在像素级别上基于不确定度来选择性交换CNN与变换器模型之间的互补特征，从而提升局部和全局表示能力。同时引入了边界敏感深度监督损失函数以进一步改善肿瘤边界的划分精度。 通过在两个临床乳腺MRI数据集上的全面实验验证，我们的方法相较于当前最先进的技术表现出更优的分割性能，突显出其在精确乳腺肿瘤描绘方面的潜在临床应用价值。
URL
https://arxiv.org/abs/2509.15758
PDF
-
FloorSAM: SAM-Guided Floorplan Reconstruction with Semantic-Geometric Fusion
2025-09-19 08:27:10Han Ye, Haofu Wang, Yunchi Zhang, Jiangjian Xiao, Yuqiang Jin, Jinyuan Liu, Wen-An Zhang, Uladzislau Sychou, Alexander Tuzikov, Vladislav Sobolevskii, Valerii Zakharov, Boris Sokolov, Minglei FuAbstract
Reconstructing building floor plans from point cloud data is key for indoor navigation, BIM, and precise measurements. Traditional methods like geometric algorithms and Mask R-CNN-based deep learning often face issues with noise, limited generalization, and loss of geometric details. We propose FloorSAM, a framework that integrates point cloud density maps with the Segment Anything Model (SAM) for accurate floor plan reconstruction from LiDAR data. Using grid-based filtering, adaptive resolution projection, and image enhancement, we create robust top-down density maps. FloorSAM uses SAM's zero-shot learning for precise room segmentation, improving reconstruction across diverse layouts. Room masks are generated via adaptive prompt points and multistage filtering, followed by joint mask and point cloud analysis for contour extraction and regularization. This produces accurate floor plans and recovers room topological relationships. Tests on Giblayout and ISPRS datasets show better accuracy, recall, and robustness than traditional methods, especially in noisy and complex settings. Code and materials: this http URL.
Abstract (translated)
从点云数据重建建筑楼层平面图是室内导航、BIM（建筑信息建模）和精确测量的关键。传统的几何算法及基于Mask R-CNN的深度学习方法在处理噪声问题时通常面临挑战，且存在泛化能力有限和几何细节丢失的问题。我们提出了FloorSAM框架，该框架将点云密度图与分割任何东西模型（Segment Anything Model, SAM）结合，用于从LiDAR数据中准确重建楼层平面图。 通过基于网格的过滤、自适应分辨率投影以及图像增强方法，我们创建了稳健的顶部视角密度图。FloorSAM利用SAM的零样本学习能力进行精确房间分割，在各种布局下提高重建精度。房间掩码是通过自适应提示点和多级过滤生成的，并随后结合掩码与点云分析提取轮廓并进行正则化处理。这种方法产生准确的楼层平面图，同时恢复房间拓扑关系。 在Giblayout和ISPRS数据集上的测试显示，FloorSAM在准确性、召回率及鲁棒性方面优于传统方法，特别是在嘈杂和复杂环境中表现尤为出色。代码与材料可在[此链接](http://this.http.url)获取。
URL
https://arxiv.org/abs/2509.15750
PDF
-
Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
2025-09-18 17:00:42Haobo Yang, Minghao Guo, Dequan Yang, Wenyu WangAbstract
Contemporary deep learning models have achieved impressive performance in image classification by primarily leveraging statistical regularities within large datasets, but they rarely incorporate structured insights drawn directly from perceptual psychology. To explore the potential of perceptually motivated inductive biases, we propose integrating classic geometric visual illusions well-studied phenomena from human perception into standard image-classification training pipelines. Specifically, we introduce a synthetic, parametric geometric-illusion dataset and evaluate three multi-source learning strategies that combine illusion recognition tasks with ImageNet classification objectives. Our experiments reveal two key conceptual insights: (i) incorporating geometric illusions as auxiliary supervision systematically improves generalization, especially in visually challenging cases involving intricate contours and fine textures; and (ii) perceptually driven inductive biases, even when derived from synthetic stimuli traditionally considered unrelated to natural image recognition, can enhance the structural sensitivity of both CNN and transformer-based architectures. These results demonstrate a novel integration of perceptual science and machine learning and suggest new directions for embedding perceptual priors into vision model design.
Abstract (translated)
现代深度学习模型通过主要利用大规模数据集中的统计规律，在图像分类任务中取得了令人印象深刻的表现，但这些模型很少直接采用从感知心理学中提取的结构化见解。为了探索由感知动机推导出的归纳偏置（inductive biases）的潜力，我们提出将经典的几何视觉错觉——即人类知觉中的经典现象——整合到标准图像分类训练流程中。具体来说，我们引入了一个合成、参数化的几何错觉数据集，并评估了三种多源学习策略，这些策略结合了对几何错觉任务的认识和ImageNet分类目标。 我们的实验揭示了两个关键概念性见解： (i) 将几何错觉作为辅助监督系统地提高了泛化能力，在涉及复杂轮廓和精细纹理的视觉挑战性案例中尤其明显； (ii) 即使源自于传统上被认为与自然图像识别无关的人工刺激物，感知驱动的归纳偏置也能增强基于卷积神经网络（CNN）和变换器架构的模型在结构敏感度上的表现。 这些结果展示了将感知科学与机器学习结合的新颖方法，并为将知觉先验嵌入视觉模型设计中提供了新的方向。
URL
https://arxiv.org/abs/2509.15156
PDF
-
Fracture interactive geodesic active contours for bone segmentation
2025-09-18 10:18:29Liheng Wang, Licheng Zhang, Hailin Xu, Jingxin Zhao, Xiuyun Su, Jiantao Li, Miutian Tang, Weilu Gao, Chong ChenAbstract
For bone segmentation, the classical geodesic active contour model is usually limited by its indiscriminate feature extraction, and then struggles to handle the phenomena of edge obstruction, edge leakage and bone fracture. Thus, we propose a fracture interactive geodesic active contour algorithm tailored for bone segmentation, which can better capture bone features and perform robustly to the presence of bone fractures and soft tissues. Inspired by orthopedic knowledge, we construct a novel edge-detector function that combines the intensity and gradient norm, which guides the contour towards bone edges without being obstructed by other soft tissues and therefore reduces mis-segmentation. Furthermore, distance information, where fracture prompts can be embedded, is introduced into the contour evolution as an adaptive step size to stabilize the evolution and help the contour stop at bone edges and fractures. This embedding provides a way to interact with bone fractures and improves the accuracy in the fracture regions. Experiments in pelvic and ankle segmentation demonstrate the effectiveness on addressing the aforementioned problems and show an accurate, stable and consistent performance, indicating a broader application in other bone anatomies. Our algorithm also provides insights into combining the domain knowledge and deep neural networks.
Abstract (translated)
对于骨骼分割，传统的几何主动轮廓模型通常受限于其无差别特征提取，并且难以处理边缘阻塞、边缘泄漏和骨裂等现象。为此，我们提出了一种针对骨骼分割的骨折交互式几何主动轮廓算法，该算法能够更好地捕捉骨骼特征并在存在骨折和软组织的情况下表现出色。 受到正畸学知识的启发，我们构建了一个新型边缘检测函数，结合了强度和梯度范数，引导轮廓向骨骼边缘移动而不被其他软组织阻碍，从而减少误分割的情况。此外，我们将距离信息引入轮廓演化过程中作为自适应步长，这些信息中可以嵌入骨折提示，以稳定演化进程并帮助轮廓在骨骼边缘和骨折处停止。这种嵌入提供了与骨裂交互的方法，并提高了骨折区域的准确性。 实验表明，在盆腔和踝部分割中的应用证明了该算法能够有效解决上述问题，并表现出准确、稳定且一致的性能，这预示着它在其他骨骼解剖学中也具有更广泛的应用前景。我们的算法还为将领域知识与深度神经网络相结合提供了新的见解。
URL
https://arxiv.org/abs/2509.14817
PDF
-
Rethinking Reference Trajectories in Agile Drone Racing: A Unified Reference-Free Model-Based Controller via MPPI
2025-09-18 08:22:08Fangguo Zhao, Xin Guan, Shuo LiAbstract
While model-based controllers have demonstrated remarkable performance in autonomous drone racing, their performance is often constrained by the reliance on pre-computed reference trajectories. Conventional approaches, such as trajectory tracking, demand a dynamically feasible, full-state reference, whereas contouring control relaxes this requirement to a geometric path but still necessitates a reference. Recent advancements in reinforcement learning (RL) have revealed that many model-based controllers optimize surrogate objectives, such as trajectory tracking, rather than the primary racing goal of directly maximizing progress through gates. Inspired by these findings, this work introduces a reference-free method for time-optimal racing by incorporating this gate progress objective, derived from RL reward shaping, directly into the Model Predictive Path Integral (MPPI) formulation. The sampling-based nature of MPPI makes it uniquely capable of optimizing the discontinuous and non-differentiable objective in real-time. We also establish a unified framework that leverages MPPI to systematically and fairly compare three distinct objective functions with a consistent dynamics model and parameter set: classical trajectory tracking, contouring control, and the proposed gate progress objective. We compare the performance of these three objectives when solved via both MPPI and a traditional gradient-based solver. Our results demonstrate that the proposed reference-free approach achieves competitive racing performance, rivaling or exceeding reference-based methods. Videos are available at this https URL
Abstract (translated)
虽然基于模型的控制器在自主无人机竞速中展现了卓越的表现，但它们的性能往往受限于对预计算参考轨迹的依赖。传统的路径跟踪方法需要动态可行且完整的状态参考，而轮廓控制则放松了这一要求，仅需几何路径作为参考，但仍存在依赖参考的问题。近期强化学习（RL）的研究表明，许多基于模型的控制器优化的是替代目标函数，例如路径跟踪，而非直接最大化通过门的速度这一主要竞速目标。受此启发，本文提出了一种无参考的方法，用于时间最优竞速，在Model Predictive Path Integral (MPPI) 方法中直接应用了从RL奖励塑形得出的门进度目标。由于MPPI方法基于采样特性，使其能够实时优化这一不连续且非可微的目标函数。此外，我们还建立了一个统一框架，利用MPPI系统地和公平地比较三种不同的目标函数，并采用一致的动力学模型和参数集：经典路径跟踪、轮廓控制以及所提出的门进度目标。在使用MPPI和传统梯度法求解时，我们评估了这三项目标函数的性能。实验结果表明，所提出的无参考方法达到了与基于参考的方法相当甚至更优的竞争性竞速表现。相关视频可在以下链接查看：[https URL]
URL
https://arxiv.org/abs/2509.14726
PDF
-
Frequency-Aware Ensemble Learning for BraTS 2025 Pediatric Brain Tumor Segmentation
2025-09-18 03:24:58Yuxiao Yi, Qingyao Zhuang, Zhi-Qin John XuAbstract
Pediatric brain tumor segmentation presents unique challenges due to the rarity and heterogeneity of these malignancies, yet remains critical for clinical diagnosis and treatment planning. We propose an ensemble approach integrating nnU-Net, Swin UNETR, and HFF-Net for the BraTS-PED 2025 challenge. Our method incorporates three key extensions: adjustable initialization scales for optimal nnU-Net complexity control, transfer learning from BraTS 2021 pre-trained models to enhance Swin UNETR's generalization on pediatric dataset, and frequency domain decomposition for HFF-Net to separate low-frequency tissue contours from high-frequency texture details. Our final ensemble combines nnU-Net ($\gamma=0.7$), fine-tuned Swin UNETR, and HFF-Net, achieving Dice scores of 72.3% (ET), 95.6% (NET), 68.9% (CC), 89.5% (ED), 92.3% (TC), and 92.3% (WT), respectively.
Abstract (translated)
儿童脑肿瘤分割由于这些恶性肿瘤的罕见性和异质性而面临独特的挑战，但它对于临床诊断和治疗计划仍然至关重要。我们为BraTS-PED 2025挑战赛提出了一种集成方法，结合了nnU-Net、Swin UNETR和HFF-Net。我们的方法包含了三个关键扩展：可调初始化尺度以实现最佳的nnU-Net复杂度控制；从BraTS 2021预训练模型中进行迁移学习以增强Swin UNETR在儿童数据集上的泛化能力；以及通过频率域分解使HFF-Net能够将低频组织轮廓与高频纹理细节分离。最终集成方法包括调整参数为$\gamma=0.7$的nnU-Net、微调后的Swin UNETR和HFF-Net，分别取得了72.3%（增强肿瘤, ET）、95.6%（非增强肿瘤, NET）、68.9%（核心肿瘤, CC）、89.5%（全脑水肿, ED）、92.3%（全肿瘤, TC）和92.3%（全病变, WT）的Dice评分。
URL
https://arxiv.org/abs/2509.19353
PDF
-
InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation
2025-09-09 14:53:19Sanyam Jain, Khuram Naveed, Illia Oleksiienko, Alexandros Iosifidis, Ruben PauwelsAbstract
This work introduces InJecteD, a framework for interpreting Denoising Diffusion Probabilistic Models (DDPMs) by analyzing sample trajectories during the denoising process of 2D point cloud generation. We apply this framework to three datasets from the Datasaurus Dozen bullseye, dino, and circle using a simplified DDPM architecture with customizable input and time embeddings. Our approach quantifies trajectory properties, including displacement, velocity, clustering, and drift field dynamics, using statistical metrics such as Wasserstein distance and cosine similarity. By enhancing model transparency, InJecteD supports human AI collaboration by enabling practitioners to debug and refine generative models. Experiments reveal distinct denoising phases: initial noise exploration, rapid shape formation, and final refinement, with dataset-specific behaviors example, bullseyes concentric convergence vs. dinos complex contour formation. We evaluate four model configurations, varying embeddings and noise schedules, demonstrating that Fourier based embeddings improve trajectory stability and reconstruction quality
Abstract (translated)
这项工作介绍了一种名为InJecteD的框架，该框架通过分析在二维点云生成过程中去噪扩散概率模型（DDPMs）样本轨迹来解释这些模型。我们使用一个简化版的具有可定制输入和时间嵌入的DDPM架构，在Datasaurus Dozen数据集中的bullseye、dino和circle三个子集中应用了这一框架。我们的方法通过诸如Wasserstein距离和余弦相似度等统计指标量化轨迹属性，包括位移、速度、聚类和漂移场动态。通过增强模型的透明性，InJecteD支持人类与AI的合作，使实践者能够调试并改进生成式模型。 实验揭示了去噪过程中的三个不同阶段：初始噪声探索期、快速形状形成期以及最终精炼期，并且这些行为会因数据集的不同而有所差异。例如，在bullseye中观察到了同心收敛的行为，而在dino中则形成了复杂的轮廓。我们评估了四种模型配置，通过改变嵌入和噪声调度来展示基于傅里叶的嵌入如何提高轨迹稳定性以及重建质量。
URL
https://arxiv.org/abs/2509.12239
PDF
-
Optimal Multi-Task Learning at Regularization Horizon for Speech Translation Task
Abstract
End-to-end speech-to-text translation typically suffers from the scarcity of paired speech-text data. One way to overcome this shortcoming is to utilize the bitext data from the Machine Translation (MT) task and perform Multi-Task Learning (MTL). In this paper, we formulate MTL from a regularization perspective and explore how sequences can be regularized within and across modalities. By thoroughly investigating the effect of consistency regularization (different modality) and R-drop (same modality), we show how they respectively contribute to the total regularization. We also demonstrate that the coefficient of MT loss serves as another source of regularization in the MTL setting. With these three sources of regularization, we introduce the optimal regularization contour in the high-dimensional space, called the regularization horizon. Experiments show that tuning the hyperparameters within the regularization horizon achieves near state-of-the-art performance on the MuST-C dataset.
Abstract (translated)
端到端的语音转文本翻译通常会受到成对的语音-文本数据稀缺性的限制。克服这一问题的一种方法是利用机器翻译（MT）任务中的双语数据，并进行多任务学习（MTL）。在这篇论文中，我们从正则化角度出发来构建多任务学习框架，并探讨了如何在不同模态内和跨模态之间对序列进行正则化。通过深入研究一致性正则化（不同模态）和R-drop（相同模态）的效果，展示了它们各自对于总正则化的贡献。我们还表明，在多任务设置中，机器翻译损失的系数充当另一种正则化来源。利用这三种正则化来源，我们在高维空间中引入了一种名为正则化地平线的最佳正则化轮廓。实验结果表明，在MuST-C数据集上调整该正则化地平线内的超参数可以实现接近最先进的性能。
URL
https://arxiv.org/abs/2509.09701
PDF
-
MedLiteNet: Lightweight Hybrid Medical Image Segmentation Model
2025-09-03 05:59:13Pengyang Yu, Haoquan Wang, Gerard Marks, Tahar Kechadi, Laurence T. Yang, Sahraoui Dhelim, Nyothiri AungAbstract
Accurate skin-lesion segmentation remains a key technical challenge for computer-aided diagnosis of skin cancer. Convolutional neural networks, while effective, are constrained by limited receptive fields and thus struggle to model long-range dependencies. Vision Transformers capture global context, yet their quadratic complexity and large parameter budgets hinder use on the small-sample medical datasets common in dermatology. We introduce the MedLiteNet, a lightweight CNN Transformer hybrid tailored for dermoscopic segmentation that achieves high precision through hierarchical feature extraction and multi-scale context aggregation. The encoder stacks depth-wise Mobile Inverted Bottleneck blocks to curb computation, inserts a bottleneck-level cross-scale token-mixing unit to exchange information between resolutions, and embeds a boundary-aware self-attention module to sharpen lesion contours.
Abstract (translated)
准确的皮肤病变分割仍然是计算机辅助诊断皮肤癌的关键技术挑战。卷积神经网络虽然有效，但由于有限的感受野而难以建模长距离依赖关系。视觉变换器能够捕捉全局上下文，但其二次复杂度和庞大的参数预算阻碍了在常见于皮肤病学的小样本医疗数据集上的应用。我们引入了MedLiteNet，这是一种轻量级的CNN-Transformer混合模型，专门用于皮肤镜检查分割，并通过分层特征提取和多尺度上下文聚合实现了高精度。编码器堆叠深度方向的Mobile Inverted Bottleneck块以减少计算成本，在瓶颈级别插入跨尺度令牌混合单元以便在不同分辨率之间交换信息，并嵌入一个边缘感知自注意力模块来锐化病变轮廓。
URL
https://arxiv.org/abs/2509.03041
PDF
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
2025-09-02 17:46:26Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Michael Littman, Jun Wang, Shuicheng Yan, Philip Torr, Lei BaiAbstract
The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the temporally extended, partially observable Markov decision processes (POMDPs) that define Agentic RL. Building on this foundation, we propose a comprehensive twofold taxonomy: one organized around core agentic capabilities, including planning, tool use, memory, reasoning, self-improvement, and perception, and the other around their applications across diverse task domains. Central to our thesis is that reinforcement learning serves as the critical mechanism for transforming these capabilities from static, heuristic modules into adaptive, robust agentic behavior. To support and accelerate future research, we consolidate the landscape of open-source environments, benchmarks, and frameworks into a practical compendium. By synthesizing over five hundred recent works, this survey charts the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose AI agents.
Abstract (translated)
代理强化学习（Agentic RL）的出现标志着从传统的大规模语言模型（LLM RL）中使用的常规强化学习向全新范式的转变，将LLM从被动的序列生成器转变为嵌入复杂动态环境中的自主决策智能体。本次综述通过对比LLM-RL中退化的单步马尔可夫决策过程（MDPs）与定义Agentic RL的扩展时间、部分可观测马尔可夫决策过程（POMDPs），正式确立了这一概念性转变。在此基础上，我们提出了一种全面的双层分类法：一个围绕核心代理能力组织，包括规划、工具使用、记忆、推理、自我改进和感知；另一个则围绕这些能力在各种任务领域中的应用进行组织。我们的主要论点是强化学习作为将这些静态、启发式模块转换为适应性强且稳健的代理行为的关键机制。 为了支持并加速未来的研究，我们将开源环境、基准测试和框架整合成一份实用的概览。通过综合分析超过五百篇近期的相关文献，本次综述勾勒出了这一迅速发展的领域的发展轮廓，并突显了将塑造可扩展通用人工智能代理开发的机会与挑战。
URL
https://arxiv.org/abs/2509.02547
PDF
-
ContextFusion and Bootstrap: An Effective Approach to Improve Slot Attention-Based Object-Centric Learning
2025-09-02 07:19:25Pinzhuo Tian, Shengjie Yang, Hang Yu, Alex C. KotAbstract
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based framework has emerged as a leading approach in this area and has been widely used in various downstream tasks. However, existing slot attention methods face two key limitations: (1) a lack of high-level semantic information. In current methods, image areas are assigned to slots based on low-level features such as color and texture. This makes the model overly sensitive to low-level features and limits its understanding of object contours, shapes, or other semantic characteristics. (2) The inability to fine-tune the encoder. Current methods require a stable feature space throughout training to enable reconstruction from slots, which restricts the flexibility needed for effective object-centric learning. To address these limitations, we propose a novel ContextFusion stage and a Bootstrap Branch, both of which can be seamlessly integrated into existing slot attention models. In the ContextFusion stage, we exploit semantic information from the foreground and background, incorporating an auxiliary indicator that provides additional contextual cues about them to enrich the semantic content beyond low-level features. In the Bootstrap Branch, we decouple feature adaptation from the original reconstruction phase and introduce a bootstrap strategy to train a feature-adaptive mechanism, allowing for more flexible adaptation. Experimental results show that our method significantly improves the performance of different SOTA slot attention models on both simulated and real-world datasets.
Abstract (translated)
人类的一个关键能力是能够将场景分解为不同的对象，并利用这些对象之间的关系来理解环境。基于此，对象中心学习（Object-centric Learning）旨在以无监督的方式模仿这一过程，在该领域中，基于槽位注意力的框架已成为一种领先的方法，并且广泛应用于各种下游任务中。然而，现有的槽位注意方法面临着两个主要限制：(1) 缺乏高层次语义信息。在当前的方法中，图像区域是根据颜色和纹理等低级特征分配给槽位的。这使得模型对低级特征过于敏感，并限制了其理解对象轮廓、形状或其他语义特性。(2) 无法微调编码器。目前的方法在整个训练过程中需要一个稳定的特征空间以实现从槽位进行重构，从而限制了有效对象中心学习所需的灵活性。 为了克服这些局限性，我们提出了一种新颖的ContextFusion阶段和Bootstrap分支，这两者都可以无缝集成到现有的槽位注意力模型中。在ContextFusion阶段中，我们利用前景和背景中的语义信息，并引入了一个辅助指示器来提供关于它们的额外上下文线索，从而超越低级特征丰富语义内容。在Bootstrap分支中，我们将特征适应与原始重构阶段解耦，并引入了一种引导策略以训练一种可自适应机制，从而允许更加灵活的适应性调整。 实验结果显示，我们的方法显著提高了不同最先进的（SOTA）槽位注意模型在模拟和现实世界数据集上的性能。
URL
https://arxiv.org/abs/2509.02032
PDF
-
MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification
2025-08-30 01:59:19Hikmat Khan, Syed Farhan Alam Zaidi, Pir Masoom Shah, Kiruthika Balakrishnan, Rabia Khan, Muhammad Waqas, Jia WuAbstract
Domain generalization in computational histopathology is hindered by heterogeneity in whole slide images (WSIs), caused by variations in tissue preparation, staining, and imaging conditions across institutions. Unlike machine learning systems, pathologists rely on domain-invariant morphological cues such as nuclear atypia (enlargement, irregular contours, hyperchromasia, chromatin texture, spatial disorganization), structural atypia (abnormal architecture and gland formation), and overall morphological atypia that remain diagnostic across diverse settings. Motivated by this, we hypothesize that explicitly modeling biologically robust nuclear morphology and spatial organization will enable the learning of cancer representations that are resilient to domain shifts. We propose MorphGen (Morphology-Guided Generalization), a method that integrates histopathology images, augmentations, and nuclear segmentation masks within a supervised contrastive learning framework. By aligning latent representations of images and nuclear masks, MorphGen prioritizes diagnostic features such as nuclear and morphological atypia and spatial organization over staining artifacts and domain-specific features. To further enhance out-of-distribution robustness, we incorporate stochastic weight averaging (SWA), steering optimization toward flatter minima. Attention map analyses revealed that MorphGen primarily relies on nuclear morphology, cellular composition, and spatial cell organization within tumors or normal regions for final classification. Finally, we demonstrate resilience of the learned representations to image corruptions (such as staining artifacts) and adversarial attacks, showcasing not only OOD generalization but also addressing critical vulnerabilities in current deep learning systems for digital pathology. Code, datasets, and trained models are available at: this https URL
Abstract (translated)
计算病理学中的领域泛化由于整个切片图像（WSIs）的异质性而受到阻碍，这种异质性是由不同机构在组织准备、染色和成像条件上的差异造成的。与机器学习系统不同，病理学家依赖于跨多种设置仍具有诊断价值的域不变形态线索，例如核异常（增大、不规则轮廓、着色加深、染色质纹理、空间失序）、结构异常（异常架构和腺体形成）以及整体形态学异常。 受此启发，我们假设显式建模生物上稳健的核形态及空间组织将能够学习到在领域变化中具有鲁棒性的癌症表示。为此，我们提出了MorphGen（基于形态特征的泛化方法），这是一种结合了病理图像、数据增强和细胞核分割掩膜，在监督对比学习框架内的方法。通过使图像与核掩模之间的潜在表征对齐，MorphGen优先考虑诊断性特征（如核异常及形态学异常以及空间组织）而非染色伪影和特定领域的特性。 为了进一步提高域外数据的稳健性，我们引入了随机权重平均化（SWA），这种方法导向寻找更平坦的极小值。注意力图分析显示，MorphGen主要依赖于肿瘤或正常区域内的核形态、细胞组成以及空间细胞组织来进行最终分类。 最后，我们展示了所学表示在面对图像损坏（如染色伪影）和对抗性攻击时的鲁棒性，不仅表现出域外泛化能力，还解决了当前数字病理学深度学习系统中的关键漏洞问题。相关代码、数据集及训练模型可从以下网址获取：[提供链接]
URL
https://arxiv.org/abs/2509.00311
PDF
-
Generative AI for Industrial Contour Detection: A Language-Guided Vision System
2025-08-29 23:58:08Liang Gong (Zelin), Tommy (Zelin), Wang, Sara Chaker, Yanchen Dong, Fouad Bousetouane, Brenden Morton, Mark MendezAbstract
Industrial computer vision systems often struggle with noise, material variability, and uncontrolled imaging conditions, limiting the effectiveness of classical edge detectors and handcrafted pipelines. In this work, we present a language-guided generative vision system for remnant contour detection in manufacturing, designed to achieve CAD-level precision. The system is organized into three stages: data acquisition and preprocessing, contour generation using a conditional GAN, and multimodal contour refinement through vision-language modeling, where standardized prompts are crafted in a human-in-the-loop process and applied through image-text guided synthesis. On proprietary FabTrack datasets, the proposed system improved contour fidelity, enhancing edge continuity and geometric alignment while reducing manual tracing. For the refinement stage, we benchmarked several vision-language models, including Google's Gemini 2.0 Flash, OpenAI's GPT-image-1 integrated within a VLM-guided workflow, and open-source baselines. Under standardized conditions, GPT-image-1 consistently outperformed Gemini 2.0 Flash in both structural accuracy and perceptual quality. These findings demonstrate the promise of VLM-guided generative workflows for advancing industrial computer vision beyond the limitations of classical pipelines.
Abstract (translated)
工业计算机视觉系统经常面临噪声、材料变化和不受控制的成像条件等问题，这些问题限制了传统边缘检测器和手工制作流水线的有效性。在这项工作中，我们提出了一种语言引导的生成式视觉系统，用于制造过程中剩余轮廓的检测，旨在达到CAD级别的精度。该系统分为三个阶段：数据采集与预处理、使用条件GAN（生成对抗网络）进行轮廓生成以及通过视觉-语言建模实现多模式轮廓细化，在这一过程中，标准化提示在人机交互流程中设计并应用到图像文本引导合成中。 在专有的FabTrack数据集上，提出的系统提高了轮廓的保真度，增强了边缘连续性和几何对齐性，并减少了手动追踪的需求。对于细化阶段，我们比较了多种视觉-语言模型，包括Google的Gemini 2.0 Flash、OpenAI的GPT-image-1（在VLM引导的工作流程中整合）和开源基线模型。在标准化条件下，GPT-image-1在结构准确性和感知质量方面始终优于Gemini 2.0 Flash。 这些发现表明了视觉语言建模指导的生成工作流在工业计算机视觉领域超越传统管道限制方面的潜力。
URL
https://arxiv.org/abs/2509.00284
PDF
-
TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank
2025-08-29 17:22:13Jiawei Liu, Jiahe Hou, Wei Wang, Jinsong Du, Yang Cong, Huijie FanAbstract
Anomaly detection, which aims to identify anomalies deviating from normal patterns, is challenging due to the limited amount of normal data available. Unlike most existing unified methods that rely on carefully designed image feature extractors and memory banks to capture logical relationships between objects, we introduce a text memory bank to enhance the detection of logical anomalies. Specifically, we propose a Three-Memory framework for Unified structural and logical Anomaly Detection (TMUAD). First, we build a class-level text memory bank for logical anomaly detection by the proposed logic-aware text extractor, which can capture rich logical descriptions of objects from input images. Second, we construct an object-level image memory bank that preserves complete object contours by extracting features from segmented objects. Third, we employ visual encoders to extract patch-level image features for constructing a patch-level memory bank for structural anomaly detection. These three complementary memory banks are used to retrieve and compare normal images that are most similar to the query image, compute anomaly scores at multiple levels, and fuse them into a final anomaly score. By unifying structural and logical anomaly detection through collaborative memory banks, TMUAD achieves state-of-the-art performance across seven publicly available datasets involving industrial and medical domains. The model and code are available at this https URL.
Abstract (translated)
异常检测旨在识别偏离正常模式的异常情况，但由于可用的正常数据量有限，这一任务颇具挑战性。与大多数现有的统一方法不同，这些方法依赖于精心设计的图像特征提取器和内存库来捕捉对象之间的逻辑关系，我们引入了一个文本内存库以增强对逻辑异常的检测能力。具体来说，我们提出了一个用于统一结构化和逻辑异常检测的三内存框架（TMUAD）。 首先，通过提出的具有逻辑感知功能的文本提取器构建了一级类别的文本记忆库，该提取器能够从输入图像中捕获对象的丰富逻辑描述。其次，我们建立了一个基于分割对象提取特征的对象级别图像记忆库，以保留完整的目标轮廓。第三，我们采用视觉编码器来提取补丁级别的图像特征，并构造一个用于结构异常检测的补丁级内存库。 这三个互补的记忆库被用来检索和比较与查询图像最相似的正常图像，在多个层面上计算异常分数并将其融合成最终的异常评分。通过利用协作记忆库统一结构化和逻辑异常检测，TMUAD在涉及工业和医疗领域的七个公开数据集上实现了最先进的性能。模型和代码可在[此处](https://this https URL)获取。
URL
https://arxiv.org/abs/2508.21795
PDF
-
Reimagining Image Segmentation using Active Contour: From Chan Vese Algorithm into a Proposal Novel Functional Loss Framework
Abstract
In this paper, we present a comprehensive study and analysis of the Chan-Vese algorithm for image segmentation. We employ a discretized scheme derived from the empirical study of the Chan-Vese model's functional energy and its partial differential equation based on its level set function. We provide a proof of the results and an implementation using MATLAB. Leveraging modern computer vision methodologies, we propose a functional segmentation loss based on active contours, utilizing this http URL and a level set based on the Chan-Vese algorithm. We compare our results with common computer vision segmentation datasets and evaluate the performance of classical loss functions against our proposed method. All code and materials used are available at this https URL.
Abstract (translated)
在这篇论文中，我们对Chan-Vese算法进行了全面的研究和分析。我们采用了一种离散化方案，该方案基于对Chan-Vese模型功能能量的实证研究以及其水平集函数的部分微分方程得出。我们提供了结果证明，并使用MATLAB进行了实现。通过利用现代计算机视觉方法，我们提出了一种基于主动轮廓的功能分割损失，结合了这个URL和基于Chan-Vese算法的水平集。我们将我们的研究成果与常见的计算机视觉分割数据集进行比较，并评估经典损失函数与我们提出的方案之间的性能差异。所有使用的代码和材料都可在该https URL处获取。
URL
https://arxiv.org/abs/2508.19946
PDF
-
ERSR: An Ellipse-constrained pseudo-label refinement and symmetric regularization framework for semi-supervised fetal head segmentation in ultrasound images
2025-08-27 12:01:57Linkuan Zhou, Zhexin Chen, Yufei Shen, Junlin Xu, Ping Xuan, Yixin Zhu, Yuqi Fang, Cong Cong, Leyi Wei, Ran Su, Jia Zhou, Qiangguo JinAbstract
Automated segmentation of the fetal head in ultrasound images is critical for prenatal monitoring. However, achieving robust segmentation remains challenging due to the poor quality of ultrasound images and the lack of annotated data. Semi-supervised methods alleviate the lack of annotated data but struggle with the unique characteristics of fetal head ultrasound images, making it challenging to generate reliable pseudo-labels and enforce effective consistency regularization constraints. To address this issue, we propose a novel semi-supervised framework, ERSR, for fetal head ultrasound segmentation. Our framework consists of the dual-scoring adaptive filtering strategy, the ellipse-constrained pseudo-label refinement, and the symmetry-based multiple consistency regularization. The dual-scoring adaptive filtering strategy uses boundary consistency and contour regularity criteria to evaluate and filter teacher outputs. The ellipse-constrained pseudo-label refinement refines these filtered outputs by fitting least-squares ellipses, which strengthens pixels near the center of the fitted ellipse and suppresses noise simultaneously. The symmetry-based multiple consistency regularization enforces multi-level consistency across perturbed images, symmetric regions, and between original predictions and pseudo-labels, enabling the model to capture robust and stable shape representations. Our method achieves state-of-the-art performance on two benchmarks. On the HC18 dataset, it reaches Dice scores of 92.05% and 95.36% with 10% and 20% labeled data, respectively. On the PSFH dataset, the scores are 91.68% and 93.70% under the same settings.
Abstract (translated)
胎儿头部在超声图像中的自动分割对于产前监测至关重要，然而由于超声图像质量差以及标注数据不足的问题，实现稳健的分割仍然具有挑战性。半监督方法可以缓解缺乏标注数据的问题，但在处理胎儿头部超声图像的独特特性时却显得力不从心，因此生成可靠的伪标签和实施有效的一致性正则化约束颇具难度。为了解决这些问题，我们提出了一种新的半监督框架ERSR（Enhanced Robust Semi-supervised Regression），用于胎儿头部超声分割。该框架包括双评分自适应过滤策略、椭圆约束的伪标签精炼以及基于对称性的多级一致性正则化。 1. 双评分自适应过滤策略利用边界一致性和轮廓规则性标准来评估和筛选教师输出。 2. 椭圆约束的伪标签精炼通过拟合最小二乘椭圆来优化这些经过筛选的输出，该方法增强了拟合椭圆中心附近的像素，并同时抑制噪声。 3. 基于对称性的多级一致性正则化在扰动图像、对称区域以及原始预测与伪标签之间强制执行多层次的一致性，使模型能够捕获稳健且稳定的形状表示。 我们的方法在两个基准数据集上达到了最先进的性能。在HC18数据集中，分别使用10%和20%的标注数据时，Dice得分分别为92.05%和95.36%；而在PSFH数据集中，在相同设置下，Dice得分为91.68%和93.70%。
URL
https://arxiv.org/abs/2508.19815
PDF
-
A Closer Look at Edema Area Segmentation in SD-OCT Images Using Adversarial Framework
2025-08-26 08:16:48Yuhui Tao, Yizhe Zhang, Qiang ChenAbstract
The development of artificial intelligence models for macular edema (ME) analy-sis always relies on expert-annotated pixel-level image datasets which are expen-sive to collect prospectively. While anomaly-detection-based weakly-supervised methods have shown promise in edema area (EA) segmentation task, their per-formance still lags behind fully-supervised approaches. In this paper, we leverage the strong correlation between EA and retinal layers in spectral-domain optical coherence tomography (SD-OCT) images, along with the update characteristics of weakly-supervised learning, to enhance an off-the-shelf adversarial framework for EA segmentation with a novel layer-structure-guided post-processing step and a test-time-adaptation (TTA) strategy. By incorporating additional retinal lay-er information, our framework reframes the dense EA prediction task as one of confirming intersection points between the EA contour and retinal layers, result-ing in predictions that better align with the shape prior of EA. Besides, the TTA framework further helps address discrepancies in the manifestations and presen-tations of EA between training and test sets. Extensive experiments on two pub-licly available datasets demonstrate that these two proposed ingredients can im-prove the accuracy and robustness of EA segmentation, bridging the gap between weakly-supervised and fully-supervised models.
Abstract (translated)
用于黄斑水肿（ME）分析的人工智能模型开发通常依赖于专家标注的像素级图像数据集，这些数据集前瞻性地收集起来成本很高。虽然基于异常检测的弱监督方法在水肿区域（EA）分割任务中显示出潜力，但它们的表现仍落后于完全监督的方法。在这篇论文中，我们利用光谱域光学相干断层扫描（SD-OCT）图像中的EA与视网膜层之间的强相关性，并结合弱监督学习的更新特性，通过一个新颖的层结构引导后处理步骤和测试时间适应（TTA）策略来增强现成的对抗框架，以改进EA分割。通过加入额外的视网膜层信息，我们的框架将密集的EA预测任务重新定义为确认EA轮廓与视网膜层交点的任务，从而产生更符合EA形状先验的预测结果。此外，TTA框架进一步帮助解决训练集和测试集中EA表现形式之间的差异。在两个公开数据集上的广泛实验表明，这两种提出的成分可以提高EA分割的准确性和鲁棒性，缩小了弱监督与完全监督模型之间的差距。
URL
https://arxiv.org/abs/2508.18790
PDF
-
A biological vision inspired framework for machine perception of abutting grating illusory contours
2025-08-24 08:45:06Xiao Zhang, Kai-Fu Yang, Xian-Shi Zhang, Hong-Zhi You, Hong-Mei Yan, Yong-Jie LiAbstract
Higher levels of machine intelligence demand alignment with human perception and cognition. Deep neural networks (DNN) dominated machine intelligence have demonstrated exceptional performance across various real-world tasks. Nevertheless, recent evidence suggests that DNNs fail to perceive illusory contours like the abutting grating, a discrepancy that misaligns with human perception patterns. Departing from previous works, we propose a novel deep network called illusory contour perception network (ICPNet) inspired by the circuits of the visual cortex. In ICPNet, a multi-scale feature projection (MFP) module is designed to extract multi-scale representations. To boost the interaction between feedforward and feedback features, a feature interaction attention module (FIAM) is introduced. Moreover, drawing inspiration from the shape bias observed in human perception, an edge detection task conducted via the edge fusion module (EFM) injects shape constraints that guide the network to concentrate on the foreground. We assess our method on the existing AG-MNIST test set and the AG-Fashion-MNIST test sets constructed by this work. Comprehensive experimental results reveal that ICPNet is significantly more sensitive to abutting grating illusory contours than state-of-the-art models, with notable improvements in top-1 accuracy across various subsets. This work is expected to make a step towards human-level intelligence for DNN-based models.
Abstract (translated)
更高的机器智能需要与人类感知和认知相匹配。深度神经网络（DNN）主导的机器智能在各种现实世界任务中表现出卓越性能。然而，最近的研究表明，DNN无法识别像相邻条栅这样的错觉轮廓，这种差异与人类感知模式不符。不同于以往的工作，我们提出了一种新的深度网络——错觉轮廓感知网络（ICPNet），它受到了视觉皮层回路的启发。在ICPNet中，设计了一个多尺度特征投影（MFP）模块来提取多尺度表示。为了增强前馈和反馈特征之间的交互作用，引入了特征互动注意模块（FIAM）。此外，借鉴人类感知中的形状偏好的观察结果，我们通过边缘融合模块（EFM）执行的边缘检测任务注入了形状约束，引导网络专注于前景。 我们在现有的AG-MNIST测试集以及本研究构建的AG-Fashion-MNIST测试集上评估了我们的方法。全面的实验结果显示，ICPNet比现有最先进的模型对相邻条栅错觉轮廓更敏感，在各种子集上的顶级准确率都有显著提高。这项工作有望使基于DNN的模型向人类级别的智能迈出一步。
URL
https://arxiv.org/abs/2508.17254
PDF
-
GPL-SLAM: A Laser SLAM Framework with Gaussian Process Based Extended Landmarks
2025-08-22 15:20:43Ali Emre Balc{\i} (TU Delft), Erhan Ege Keyvan (Middle East Technical University), Emre \"Ozkan (Middle East Technical University)Abstract
We present a novel Simultaneous Localization and Mapping (SLAM) method that employs Gaussian Process (GP) based landmark (object) representations. Instead of conventional grid maps or point cloud registration, we model the environment on a per object basis using GP based contour representations. These contours are updated online through a recursive scheme, enabling efficient memory usage. The SLAM problem is formulated within a fully Bayesian framework, allowing joint inference over the robot pose and object based map. This representation provides semantic information such as the number of objects and their areas, while also supporting probabilistic measurement to object associations. Furthermore, the GP based contours yield confidence bounds on object shapes, offering valuable information for downstream tasks like safe navigation and exploration. We validate our method on synthetic and real world experiments, and show that it delivers accurate localization and mapping performance across diverse structured environments.
Abstract (translated)
我们提出了一种新颖的同时定位与地图构建（SLAM）方法，该方法采用了基于高斯过程（GP）的地标（对象）表示。不同于传统的网格地图或点云配准，我们利用基于GP的轮廓表示在每个对象的基础上建模环境。这些轮廓通过递归方案在线更新，从而实现高效的内存使用。我们将SLAM问题在一个完整的贝叶斯框架中进行表述，这使得机器人姿态和基于对象的地图可以同时推断出来。这种表示不仅提供了语义信息，如对象的数量及其面积，还支持对测量与对象关联的概率评估。此外，基于GP的轮廓能够提供关于物体形状的信心界限，这对下游任务（例如安全导航和探索）非常有用。我们在合成数据集和真实世界实验中验证了该方法，并证明它能够在各种结构化环境中实现准确的定位和地图构建性能。
URL
https://arxiv.org/abs/2508.16459
PDF
