Contour
-
FedDA-TSformer: Federated Domain Adaptation with Vision TimeSformer for Left Ventricle Segmentation on Gated Myocardial Perfusion SPECT Image
2025-02-23 20:47:37Yehong Huang, Chen Zhao, Rochak Dhakal, Min Zhao, Guang-Uei Hung, Zhixin Jiang, Weihua ZhouAbstract
Background and Purpose: Functional assessment of the left ventricle using gated myocardial perfusion (MPS) single-photon emission computed tomography relies on the precise extraction of the left ventricular contours while simultaneously ensuring the security of patient data. Methods: In this paper, we introduce the integration of Federated Domain Adaptation with TimeSformer, named 'FedDA-TSformer' for left ventricle segmentation using MPS. FedDA-TSformer captures spatial and temporal features in gated MPS images, leveraging spatial attention, temporal attention, and federated learning for improved domain adaptation while ensuring patient data security. In detail, we employed Divide-Space-Time-Attention mechanism to extract spatio-temporal correlations from the multi-centered MPS datasets, ensuring that predictions are spatio-temporally consistent. To achieve domain adaptation, we align the model output on MPS from three different centers using local maximum mean discrepancy (LMMD) loss. This approach effectively addresses the dual requirements of federated learning and domain adaptation, enhancing the model's performance during training with multi-site datasets while ensuring the protection of data from different hospitals. Results: Our FedDA-TSformer was trained and evaluated using MPS datasets collected from three hospitals, comprising a total of 150 subjects. Each subject's cardiac cycle was divided into eight gates. The model achieved Dice Similarity Coefficients (DSC) of 0.842 and 0.907 for left ventricular (LV) endocardium and epicardium segmentation, respectively. Conclusion: Our proposed FedDA-TSformer model addresses the challenge of multi-center generalization, ensures patient data privacy protection, and demonstrates effectiveness in left ventricular (LV) segmentation.
Abstract (translated)
背景和目的：使用门控心肌灌注（MPS）单光子发射计算机断层扫描评估左心室功能，需要精确提取左心室轮廓并同时确保患者数据的安全性。 方法：本文介绍了将联邦领域适应与TimeSformer结合的方法，命名为“FedDA-TSformer”，用于基于MPS的左心室分割。 FedDA-TSformer能够捕捉门控MPS图像中的空间和时间特征，并利用空间注意力、时间注意力及联邦学习来提高域适应能力，同时确保患者数据的安全性。具体来说，我们采用了Divide-Space-Time-Attention机制从多中心的MPS数据集中提取时空关联，以确保预测在时间和空间上的一致性。为了实现领域适应，我们在三个不同中心的MPS图像上对模型输出进行局部最大平均差异（LMMD）损失对齐，从而有效地解决了联邦学习和领域适应的双重需求，在训练期间使用多站点数据集时提高了模型性能，并确保了来自不同医院的数据安全。 结果：我们的FedDA-TSformer使用从三个医院收集的MPS数据集进行了训练和评估，总共有150个受试者。每个受试者的整个心动周期被分为八个门控区间。该模型在左心室（LV）内膜和外膜分割上分别达到了Dice相似系数(DSC)为0.842 和 0.907。 结论：我们提出的FedDA-TSformer模型解决了多中心泛化挑战，确保了患者数据隐私保护，并且在左心室(LV)分割方面表现出有效性。
URL
https://arxiv.org/abs/2502.16709
PDF
-
Motion-Coupled Mapping Algorithm for Hybrid Rice Canopy
2025-02-22 08:12:23Huaiqu Feng, Guoyang Zhao, Cheng Liu, Yongwei Wang, Jun WangAbstract
This paper presents a motion-coupled mapping algorithm for contour mapping of hybrid rice canopies, specifically designed for Agricultural Unmanned Ground Vehicles (Agri-UGV) navigating complex and unknown rice fields. Precise canopy mapping is essential for Agri-UGVs to plan efficient routes and avoid protected zones. The motion control of Agri-UGVs, tasked with impurity removal and other operations, depends heavily on accurate estimation of rice canopy height and structure. To achieve this, the proposed algorithm integrates real-time RGB-D sensor data with kinematic and inertial measurements, enabling efficient mapping and proprioceptive localization. The algorithm produces grid-based elevation maps that reflect the probabilistic distribution of canopy contours, accounting for motion-induced uncertainties. It is implemented on a high-clearance Agri-UGV platform and tested in various environments, including both controlled and dynamic rice field settings. This approach significantly enhances the mapping accuracy and operational reliability of Agri-UGVs, contributing to more efficient autonomous agricultural operations.
Abstract (translated)
本文提出了一种针对杂交水稻冠层轮廓绘制的运动耦合映射算法，专门设计用于在复杂且未知的稻田中导航的农业无人地面车辆（Agri-UGV）。精确的冠层地图对于Agri-UGVs规划高效路线和避开保护区至关重要。负责清除杂质和其他操作的Agri-UGVs的运动控制严重依赖于准确估计水稻冠层高度和结构的能力。为了实现这一目标，所提出的算法将实时RGB-D传感器数据与运动学和惯性测量相结合，从而能够进行高效的映射并实现自我定位。该算法生成基于网格的高度地图，反映了冠层轮廓的概率分布，并考虑了由运动引起的不确定性。此算法已在高通过性的Agri-UGV平台上实施，并在各种环境（包括受控和动态稻田设置）中进行了测试。这种方法显著提高了Agri-UGVs的映射精度和操作可靠性，有助于实现更高效的自主农业作业。
URL
https://arxiv.org/abs/2502.16134
PDF
-
3D Shape-to-Image Brownian Bridge Diffusion for Brain MRI Synthesis from Cortical Surfaces
2025-02-18 10:59:04Fabian Bongratz, Yitong Li, Sama Elbaroudy, Christian WachingerAbstract
Despite recent advances in medical image generation, existing methods struggle to produce anatomically plausible 3D structures. In synthetic brain magnetic resonance images (MRIs), characteristic fissures are often missing, and reconstructed cortical surfaces appear scattered rather than densely convoluted. To address this issue, we introduce Cor2Vox, the first diffusion model-based method that translates continuous cortical shape priors to synthetic brain MRIs. To achieve this, we leverage a Brownian bridge process which allows for direct structured mapping between shape contours and medical images. Specifically, we adapt the concept of the Brownian bridge diffusion model to 3D and extend it to embrace various complementary shape representations. Our experiments demonstrate significant improvements in the geometric accuracy of reconstructed structures compared to previous voxel-based approaches. Moreover, Cor2Vox excels in image quality and diversity, yielding high variation in non-target structures like the skull. Finally, we highlight the capability of our approach to simulate cortical atrophy at the sub-voxel level. Our code is available at this https URL.
Abstract (translated)
尽管在医学图像生成领域取得了近期进展，现有方法仍难以产生解剖学上合理的3D结构。在合成大脑磁共振成像（MRI）中，特征性裂隙常常缺失，重建的皮层表面显得分散而不是密集曲折。为解决这一问题，我们引入了Cor2Vox——首个基于扩散模型的方法，将连续的皮层形状先验转化为合成的大脑MRIs。为此，我们利用布朗桥过程，该过程允许在形状轮廓和医学图像之间进行直接结构化映射。具体而言，我们将布朗桥扩散模型的概念扩展到3D，并进一步拓展以适应各种互补的形状表示方式。 实验结果显示，与以前基于体素的方法相比，我们的方法在重建结构的几何准确性方面取得了显著改进。此外，Cor2Vox在图像质量和多样性上表现出色，在如颅骨等非目标结构中产生了高变异性。最后，我们强调了该方法模拟亚体素级皮层萎缩的能力。 我们的代码可在[此处](https://this-is-the-url-of-the-code-repository)获取。
URL
https://arxiv.org/abs/2502.12742
PDF
-
Uncertainty Propagation for Echocardiography Clinical Metric Estimation via Contour Sampling
2025-02-18 10:26:16Thierry Judge, Olivier Bernard, Woo-Jin Cho Kim, Alberto Gomez, Arian Beqiri, Agisilaos Chartsias, Pierre-Marc JodoinAbstract
Echocardiography plays a fundamental role in the extraction of important clinical parameters (e.g. left ventricular volume and ejection fraction) required to determine the presence and severity of heart-related conditions. When deploying automated techniques for computing these parameters, uncertainty estimation is crucial for assessing their utility. Since clinical parameters are usually derived from segmentation maps, there is no clear path for converting pixel-wise uncertainty values into uncertainty estimates in the downstream clinical metric calculation. In this work, we propose a novel uncertainty estimation method based on contouring rather than segmentation. Our method explicitly predicts contour location uncertainty from which contour samples can be drawn. Finally, the sampled contours can be used to propagate uncertainty to clinical metrics. Our proposed method not only provides accurate uncertainty estimations for the task of contouring but also for the downstream clinical metrics on two cardiac ultrasound datasets. Code is available at: this https URL.
Abstract (translated)
超声心动图在提取重要临床参数（例如左心室容积和射血分数）方面起着核心作用，这些参数用于确定心脏相关疾病的性质和严重程度。当部署自动技术来计算这些参数时，不确定性估计对于评估其效用至关重要。由于临床参数通常由分割地图导出，因此没有明确的方法将像素级别的不确定性值转换为下游临床度量计算中的不确定性估算。 在本工作中，我们提出了一种基于轮廓而不是分割的新型不确定性估计算法。我们的方法能够直接预测轮廓位置的不确定性，并从中抽取轮廓样本。最终，可以利用这些抽样轮廓来传播到下游临床指标中的不确定性。所提出的这种方法不仅为轮廓任务提供了准确的不确定性估计，而且在两个心脏超声数据集上的下游临床度量上也表现出色。 代码可在此网址获取：[此链接](this https URL)。
URL
https://arxiv.org/abs/2502.12713
PDF
-
Sensing-based Robustness Challenges in Agricultural Robotic Harvesting
2025-02-18 00:32:32C. Beldek, J. Cunningham, M. Aydin, E. Sariyildiz, S. L. Phung, G. AliciAbstract
This paper presents the challenges agricultural robotic harvesters face in detecting and localising fruits under various environmental disturbances. In controlled laboratory settings, both the traditional HSV (Hue Saturation Value) transformation and the YOLOv8 (You Only Look Once) deep learning model were employed. However, only YOLOv8 was utilised in outdoor experiments, as the HSV transformation was not capable of accurately drawing fruit contours. Experiments include ten distinct fruit patterns with six apples and six oranges. A grid structure for homography (perspective) transformation was employed to convert detected midpoints into 3D world coordinates. The experiments evaluated detection and localisation under varying lighting and background disturbances, revealing accurate performance indoors, but significant challenges outdoors. Our results show that indoor experiments using YOLOv8 achieved 100% detection accuracy, while outdoor conditions decreased performance, with an average accuracy of 69.15% for YOLOv8 under direct sunlight. The study demonstrates that real-world applications reveal significant limitations due to changing lighting, background disturbances, and colour and shape variability. These findings underscore the need for further refinement of algorithms and sensors to enhance the robustness of robotic harvesters for agricultural use.
Abstract (translated)
本文介绍了农业机器人收割机在各种环境干扰下检测和定位水果时所面临的挑战。在受控实验室环境中，既使用了传统的HSV（色相饱和度值）转换方法，也采用了YOLOv8（你只需看一次）深度学习模型。然而，在户外实验中仅使用了YOLOv8，因为HSV转换方法无法准确描绘出水果的轮廓。实验包括十种不同的水果图案，其中包含六只苹果和六只橙子。为了将检测到的中心点转化为三维世界坐标，采用了网格结构进行同态（透视）变换。这些实验评估了在不同光照和背景干扰条件下水果的检测与定位情况，结果表明，在室内环境下表现准确，但在户外环境下面临重大挑战。我们的结果显示，在使用YOLOv8的情况下，室内实验实现了100%的检测准确性，而室外条件下的性能有所下降，平均而言，在直接阳光下时YOLOv8的表现为69.15%的精度。这项研究展示了真实世界的应用揭示了由于光照变化、背景干扰和颜色与形状变异所导致的重要限制。这些发现强调了为了增强农业用途中机器人收割机的鲁棒性，进一步完善算法和传感器的需求。
URL
https://arxiv.org/abs/2502.12403
PDF
-
Robust 6DoF Pose Tracking Considering Contour and Interior Correspondence Uncertainty for AR Assembly Guidance
2025-02-17 16:18:57Jixiang Chen, Jing Chen, Kai Liu, Haochen Chang, Shanfeng Fu, Jian YangAbstract
Augmented reality assembly guidance is essential for intelligent manufacturing and medical applications, requiring continuous measurement of the 6DoF poses of manipulated objects. Although current tracking methods have made significant advancements in accuracy and efficiency, they still face challenges in robustness when dealing with cluttered backgrounds, rotationally symmetric objects, and noisy sequences. In this paper, we first propose a robust contour-based pose tracking method that addresses error-prone contour correspondences and improves noise tolerance. It utilizes a fan-shaped search strategy to refine correspondences and models local contour shape and noise uncertainty as mixed probability distribution, resulting in a highly robust contour energy function. Secondly, we introduce a CPU-only strategy to better track rotationally symmetric objects and assist the contour-based method in overcoming local minima by exploring sparse interior correspondences. This is achieved by pre-sampling interior points from sparse viewpoint templates offline and using the DIS optical flow algorithm to compute their correspondences during tracking. Finally, we formulate a unified energy function to fuse contour and interior information, which is solvable using a re-weighted least squares algorithm. Experiments on public datasets and real scenarios demonstrate that our method significantly outperforms state-of-the-art monocular tracking methods and can achieve more than 100 FPS using only a CPU.
Abstract (translated)
增强现实装配指导在智能制造和医疗应用中至关重要，需要连续测量操作对象的6自由度（6DoF）姿态。尽管当前的跟踪方法已经在准确性和效率方面取得了显著进展，但在处理杂乱背景、旋转对称物体以及噪声序列时仍面临鲁棒性挑战。 本文首先提出了一种基于轮廓的稳健姿态跟踪方法，该方法解决了容易出错的轮廓对应关系，并提高了抗噪能力。它采用扇形搜索策略来细化对应关系，并将局部轮廓形状和噪声不确定性建模为混合概率分布，从而形成一个高度健壮的轮廓能量函数。 其次，我们引入了一种仅使用CPU的战略，以更好地跟踪旋转对称物体，并通过探索稀疏内部对应关系帮助基于轮廓的方法克服局部极小值问题。这通过在离线阶段从稀疏视点模板中预采样内部点并在追踪过程中利用DIS光流算法计算它们的对应关系来实现。 最后，我们提出了一个统一的能量函数来融合轮廓和内部信息，并使用重新加权最小二乘法求解该能量函数。 公开数据集和真实场景中的实验表明，与最先进的单目跟踪方法相比，我们的方法表现出显著的优势，并且仅使用CPU即可达到每秒100帧以上的性能。
URL
https://arxiv.org/abs/2502.11971
PDF
-
Medical Image Registration Meets Vision Foundation Model: Prototype Learning and Contour Awareness
2025-02-17 04:54:47Hao Xu, Tengfei Xue, Jianan Fan, Dongnan Liu, Yuqian Chen, Fan Zhang, Carl-Fredrik Westin, Ron Kikinis, Lauren J. O'Donnell, Weidong CaiAbstract
Medical image registration is a fundamental task in medical image analysis, aiming to establish spatial correspondences between paired images. However, existing unsupervised deformable registration methods rely solely on intensity-based similarity metrics, lacking explicit anatomical knowledge, which limits their accuracy and robustness. Vision foundation models, such as the Segment Anything Model (SAM), can generate high-quality segmentation masks that provide explicit anatomical structure knowledge, addressing the limitations of traditional methods that depend only on intensity similarity. Based on this, we propose a novel SAM-assisted registration framework incorporating prototype learning and contour awareness. The framework includes: (1) Explicit anatomical information injection, where SAM-generated segmentation masks are used as auxiliary inputs throughout training and testing to ensure the consistency of anatomical information; (2) Prototype learning, which leverages segmentation masks to extract prototype features and aligns prototypes to optimize semantic correspondences between images; and (3) Contour-aware loss, a contour-aware loss is designed that leverages the edges of segmentation masks to improve the model's performance in fine-grained deformation fields. Extensive experiments demonstrate that the proposed framework significantly outperforms existing methods across multiple datasets, particularly in challenging scenarios with complex anatomical structures and ambiguous boundaries. Our code is available at this https URL.
Abstract (translated)
医学图像配准是医学图像分析中的基本任务，旨在建立成对图像之间的空间对应关系。然而，现有的无监督可变形配准方法仅依赖于基于强度的相似性度量，缺乏显式的解剖学知识，这限制了它们的准确性和鲁棒性。视觉基础模型，如Segment Anything Model (SAM)，可以生成高质量的分割掩码，提供明确的解剖结构知识，从而克服了传统方法单纯依靠强度相似性的局限性。基于此，我们提出了一种新的SAM辅助配准框架，该框架结合了原型学习和轮廓感知功能。该框架包括： 1. 显式解剖信息注入：使用由SAM生成的分割掩码作为在整个训练和测试过程中使用的辅助输入，以确保解剖学信息的一致性。 2. 原型学习：利用分割掩码提取原型特征，并对齐这些原型以优化图像之间的语义对应关系。 3. 轮廓感知损失：设计了一种轮廓感知损失函数，该函数利用分割掩码的边缘来提高模型在精细变形场中的性能。 广泛的实验表明，所提出的框架在多个数据集上显著优于现有方法，特别是在具有复杂解剖结构和模糊边界等挑战性场景中。我们的代码可在[此链接](https://this https URL)获取。
URL
https://arxiv.org/abs/2502.11440
PDF
-
SIToBI - A Speech Prosody Annotation Tool for Indian Languages
2025-02-12 08:29:00Preethi Thinakaran, Malarvizhi Muthuramalingam, Sooriya S, Anushiya Rachel Gladston, P. Vijayalakshmi, Hema A Murthy, T. NagarajanAbstract
The availability of prosodic information from speech signals is useful in a wide range of applications. However, deriving this information from speech signals can be a laborious task involving manual intervention. Therefore, the current work focuses on developing a tool that can provide prosodic annotations corresponding to a given speech signal, particularly for Indian languages. The proposed Segmentation with Intensity, Tones and Break Indices (SIToBI) tool provides time-aligned phoneme, syllable, and word transcriptions, syllable-level pitch contour annotations, break indices, and syllable-level relative intensity indices. The tool focuses more on syllable-level annotations since Indian languages are syllable-timed. Indians, regardless of the language they speak, may exhibit influences from other languages. As a result, other languages spoken in India may also exhibit syllable-timed characteristics. The accuracy of the annotations derived from the tool is analyzed by comparing them against manual annotations and the tool is observed to perform well. While the current work focuses on three languages, namely, Tamil, Hindi, and Indian English, the tool can easily be extended to other Indian languages and possibly other syllable-timed languages as well.
Abstract (translated)
从语音信号中提取韵律信息在各种应用场景中有用，然而，从这些信号中推导出这类信息可能是一项需要大量人工干预的繁重任务。因此，当前的工作重点是开发一种工具，用于为给定的语音信号提供韵律标注，特别是针对印度语言。所提出的强度、声调和停顿索引分段（Segmentation with Intensity, Tones and Break Indices，简称SIToBI）工具提供了与时间对齐的音素、音节和单词转录，音节级别的语调轮廓标注，停顿指数以及音节级别的相对强度指数。 该工具有针对性地提供更多的音节级别注释，因为印度语言通常是音节计时的。无论讲何种语言，印度人都可能受到其他语言的影响，因此在印度使用的其他语言也可能表现出音节计时的特点。通过将工具生成的标注与手动标注进行比较来分析其准确性，并且发现该工具表现良好。 虽然当前的工作重点是三种语言，即泰米尔语、印地语和印度英语，但该工具也可以轻松扩展到其他印度语言及其他音节计时的语言中使用。
URL
https://arxiv.org/abs/2502.09661
PDF
-
An inpainting approach to manipulate asymmetry in pre-operative breast images
2025-02-08 17:54:11Helena Montenegro, Maria J. Cardoso, Jaime S. CardosoAbstract
One of the most frequent modalities of breast cancer treatment is surgery. Breast surgery can cause visual alterations to the breasts, due to scars and asymmetries. To enable an informed choice of treatment, the patient must be adequately informed of the aesthetic outcomes of each treatment plan. In this work, we propose an inpainting approach to manipulate breast shape and nipple position in breast images, for the purpose of predicting the aesthetic outcomes of breast cancer treatment. We perform experiments with various model architectures for the inpainting task, including invertible networks capable of manipulating breasts in the absence of ground-truth breast contour and nipple annotations. Experiments on two breast datasets show the proposed models' ability to realistically alter a patient's breasts, enabling a faithful reproduction of breast asymmetries of post-operative patients in pre-operative images.
Abstract (translated)
乳腺癌治疗中最常见的方法之一是手术。乳房手术可能会由于疤痕和不对称而导致视觉变化。为了使患者能够做出知情的治疗选择，必须充分告知他们每种治疗方案的美学效果。在这项工作中，我们提出了一种图像修复方法，用于操纵乳房形状和乳头位置，以预测乳腺癌治疗的美学结果。我们在各种模型架构上进行了实验，这些模型用于执行没有真实乳房轮廓和乳头注释情况下的乳房操作任务，包括能够在这种情况下操作乳房的可逆网络。在两个乳房数据集上的实验证明了所提出的模型有能力现实地改变患者的乳房，使术前图像中术后患者乳房不对称的真实再现成为可能。
URL
https://arxiv.org/abs/2502.05652
PDF
-
Reduce Lap Time for Autonomous Racing with Curvature-Integrated MPCC Local Trajectory Planning Method
2025-02-06 01:03:54Zhouheng Li, Lei Xie, Cheng Hu, Hongye SuAbstract
The widespread application of autonomous driving technology has significantly advanced the field of autonomous racing. Model Predictive Contouring Control (MPCC) is a highly effective local trajectory planning method for autonomous racing. However, the traditional MPCC method struggles with racetracks that have significant curvature changes, limiting the performance of the vehicle during autonomous racing. To address this issue, we propose a curvature-integrated MPCC (CiMPCC) local trajectory planning method for autonomous racing. This method optimizes the velocity of the local trajectory based on the curvature of the racetrack centerline. The specific implementation involves mapping the curvature of the racetrack centerline to a reference velocity profile, which is then incorporated into the cost function for optimizing the velocity of the local trajectory. This reference velocity profile is created by normalizing and mapping the curvature of the racetrack centerline, thereby ensuring efficient and performance-oriented local trajectory planning in racetracks with significant curvature. The proposed CiMPCC method has been experimented on a self-built 1:10 scale F1TENTH racing vehicle deployed with ROS platform. The experimental results demonstrate that the proposed method achieves outstanding results on a challenging racetrack with sharp curvature, improving the overall lap time by 11.4%-12.5% compared to other autonomous racing trajectory planning methods. Our code is available at this https URL.
Abstract (translated)
自主驾驶技术的广泛应用极大地推动了自动驾驶赛车领域的发展。模型预测轮廓控制（Model Predictive Contouring Control，MPCC）是一种非常有效的局部路径规划方法，在自动驾驶赛车中尤为突出。然而，传统的 MPCC 方法在处理赛道曲率变化显著的情况下表现不佳，这限制了车辆在自主赛车中的性能。为了解决这个问题，我们提出了一种基于曲率的 MPCC（Curvature-integrated Model Predictive Contouring Control, CiMPCC）局部路径规划方法用于自动驾驶赛车。该方法根据赛道中心线的曲率优化局部轨迹的速度。 具体实现包括将赛道中心线的曲率映射到参考速度曲线，然后将其纳入成本函数中以优化局部轨迹的速度。通过归一化和映射赛道中心线的曲率来创建这一参考速度曲线，从而确保在曲率显著变化的赛道上进行高效且性能导向的局部路径规划。 我们在一个自制的 1:10 比例 F1TENTH 赛车（搭载 ROS 平台）上对所提出的 CiMPCC 方法进行了实验。实验结果表明，在一条具有急转弯挑战性的赛道中，该方法取得了卓越的成绩，相较于其他自动驾驶赛车路径规划方法，整体圈速提高了 11.4% 至 12.5%。 我们的代码可在以下网址获取：[此链接](https://this https URL)（请注意，实际提供有效网址）。
URL
https://arxiv.org/abs/2502.03695
PDF
-
Deep Learning Pipeline for Fully Automated Myocardial Infarct Segmentation from Clinical Cardiac MR Scans
2025-02-05 15:29:28Matthias Schwab, Mathias Pamminger, Christian Kremser, Agnes MayrAbstract
Purpose: To develop and evaluate a deep learning-based method that allows to perform myocardial infarct segmentation in a fully-automated way. Materials and Methods: For this retrospective study, a cascaded framework of two and three-dimensional convolutional neural networks (CNNs), specialized on identifying ischemic myocardial scars on late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) images, was trained on an in-house training dataset consisting of 144 examinations. On a separate test dataset from the same institution, including images from 152 examinations obtained between 2021 and 2023, a quantitative comparison between artificial intelligence (AI)-based segmentations and manual segmentations was performed. Further, qualitative assessment of segmentation accuracy was evaluated for both human and AI-generated contours by two CMR experts in a blinded experiment. Results: Excellent agreement could be found between manually and automatically calculated infarct volumes ($\rho_c$ = 0.9). The qualitative evaluation showed that compared to human-based measurements, the experts rated the AI-based segmentations to better represent the actual extent of infarction significantly (p < 0.001) more often (33.4% AI, 25.1% human, 41.5% equal). On the contrary, for segmentation of microvascular obstruction (MVO), manual measurements were still preferred (11.3% AI, 55.6% human, 33.1% equal). Conclusion: This fully-automated segmentation pipeline enables CMR infarct size to be calculated in a very short time and without requiring any pre-processing of the input images while matching the segmentation quality of trained human observers. In a blinded experiment, experts preferred automated infarct segmentations more often than manual segmentations, paving the way for a potential clinical application.
Abstract (translated)
目的：开发并评估一种基于深度学习的方法，用于全自动的心肌梗死分割。 材料和方法：在这项回顾性研究中，研究人员使用了一个由两家医院内部数据集训练的级联框架（包括二维和三维卷积神经网络），该框架专门针对在延迟钆增强心脏磁共振成像（LGE CMR）图像上识别心肌缺血疤痕进行优化。训练数据集包含144个检查案例。在一个独立的数据集中进行了定量比较，这个测试数据集来自同一个机构，包括2021年至2023年间获取的152张图像。此外，在一个双盲实验中，由两位CMR专家对人类和AI生成轮廓的分割准确性的定性评估进行了评价。 结果：手动计算的心肌梗死体积与自动计算的结果之间具有很好的一致性（$ρ_c$ = 0.9）。在定性评价方面，专家们认为AI基础的分割比基于人的测量更精确地代表了心肌梗塞的实际范围，这一结论显著得多（p < 0.001），具体来说，33.4%的情况是AI优于人类，25.1%的情况是人工优于AI，而两者相等的情况下占41.5%。然而，在微血管障碍（MVO）的分割方面，手动测量仍然更受欢迎（分别为11.3%，55.6%和33.1%）。 结论：这种全自动的心肌梗死分割管道可以在极短的时间内计算CMR心肌梗死大小，并且无需对输入图像进行任何预处理，同时与训练有素的人类观察者的分割质量相匹配。在双盲实验中，专家们更倾向于选择自动化的梗死分割结果而非手动的分割结果，这为潜在的临床应用铺平了道路。
URL
https://arxiv.org/abs/2502.03272
PDF
-
Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches
2025-01-31 17:26:40Ying Zang, Runlong Cao, Jianqi Zhang, Yidong Han, Ziyue Cao, Wenjun Hu, Didi Zhu, Lanyun Zhu, Zejian Li, Deyi Ji, Tianrun ChenAbstract
Sketches, with their expressive potential, allow humans to convey the essence of an object through even a rough contour. For the first time, we harness this expressive potential to improve segmentation performance in challenging tasks like camouflaged object detection (COD). Our approach introduces an innovative sketch-guided interactive segmentation framework, allowing users to intuitively annotate objects with freehand sketches (drawing a rough contour of the object) instead of the traditional bounding boxes or points used in classic interactive segmentation models like SAM. We demonstrate that sketch input can significantly improve performance in existing iterative segmentation methods, outperforming text or bounding box annotations. Additionally, we introduce key modifications to network architectures and a novel sketch augmentation technique to fully harness the power of sketch input and further boost segmentation accuracy. Remarkably, our model' s output can be directly used to train other neural networks, achieving results comparable to pixel-by-pixel annotations--while reducing annotation time by up to 120 times, which shows great potential in democratizing the annotation process and enabling model training with less reliance on resource-intensive, laborious pixel-level annotations. We also present KOSCamo+, the first freehand sketch dataset for camouflaged object detection. The dataset, code, and the labeling tool will be open sourced.
Abstract (translated)
草图，凭借其强大的表现力，允许人类通过粗糙的轮廓来传达一个物体的本质。首次，我们利用这一表现潜力以提升在具有挑战性的任务如伪装目标检测（COD）中的分割性能。我们的方法引入了一个创新的基于草图引导的交互式分割框架，该框架让用户能够用自由手绘的草图（绘制物体的大致轮廓），而不是经典交互式分割模型如SAM中使用的传统边界框或点，来进行直观地标注对象。 我们展示了草图输入可以显著提升现有迭代分割方法的表现，并且在现有的文本或边界框注释方式下表现更佳。此外，我们对网络架构进行了关键修改，并引入了一种新颖的草图增强技术，以充分利用草图输入并进一步提高分割准确性。令人印象深刻的是，我们的模型输出可以直接用于训练其他神经网络，在结果上媲美逐像素标注—同时将标注时间减少多达120倍，这显示了在注释过程中实现民主化以及使模型训练更少依赖于资源密集型、劳动密集的逐像素级标注方面具有巨大潜力。 此外，我们还发布了KOSCamo+，这是首个用于伪装目标检测的手绘草图数据集。该数据集、代码和标记工具将会开源提供。
URL
https://arxiv.org/abs/2501.19329
PDF
-
ContourFormer:Real-Time Contour-Based End-to-End Instance Segmentation Transformer
2025-01-29 14:56:27Weiwei yao, Chen Li, Minjun Xiong, Wenbo Dong, Hao Chen, Xiong XiaoAbstract
This paper presents Contourformer, a real-time contour-based instance segmentation algorithm. The method is fully based on the DETR paradigm and achieves end-to-end inference through iterative and progressive mechanisms to optimize contours. To improve efficiency and accuracy, we develop two novel techniques: sub-contour decoupling mechanisms and contour fine-grained distribution this http URL the sub-contour decoupling mechanism, we propose a deformable attention-based module that adaptively selects sampling regions based on the current predicted contour, enabling more effective capturing of object boundary information. Additionally, we design a multi-stage optimization process to enhance segmentation precision by progressively refining sub-contours. The contour fine-grained distribution refinement technique aims to further improve the ability to express fine details of this http URL innovations enable Contourformer to achieve stable and precise segmentation for each instance while maintaining real-time performance. Extensive experiments demonstrate the superior performance of Contourformer on multiple benchmark datasets, including SBD, COCO, and KINS. We conduct comprehensive evaluations and comparisons with existing state-of-the-art methods, showing significant improvements in both accuracy and inference this http URL work provides a new solution for contour-based instance segmentation tasks and lays a foundation for future research, with the potential to become a strong baseline method in this field.
Abstract (translated)
这篇论文提出了Contourformer，一种基于轮廓的实时实例分割算法。该方法完全基于DETR范式，并通过迭代和渐进机制优化轮廓实现端到端推理。为了提高效率和精度，我们开发了两项新技术：子轮廓解耦机制和轮廓细粒度分布细化技术。 在子轮廓解耦机制中，我们提出了一种基于可变形注意力的模块，该模块能够根据当前预测的轮廓自适应地选择采样区域，从而更有效地捕捉物体边界信息。此外，我们设计了一个多阶段优化过程，通过逐步精炼子轮廓来提高分割精度。轮廓细粒度分布细化技术旨在进一步增强对细微细节表达的能力。 这些创新使Contourformer能够为每个实例实现稳定而精确的分割，并保持实时性能。广泛的实验表明，在SBD、COCO和KINS等多个基准数据集上，Contourformer具有优越的表现。我们进行了全面的评估和与现有最新方法的比较，证明了在精度和推理速度方面有显著改进。 这项工作为基于轮廓的实例分割任务提供了新的解决方案，并为未来的研究奠定了基础，有望成为该领域的强大基线方法。
URL
https://arxiv.org/abs/2501.17688
PDF
-
Multi-Objective Deep-Learning-based Biomechanical Deformable Image Registration with MOREA
2025-01-27 21:50:12Georgios Andreadis, Eduard Ruiz Munn\'e, Thomas H. W. B\"ack, Peter A. N. Bosman, Tanja AlderliestenAbstract
When choosing a deformable image registration (DIR) approach for images with large deformations and content mismatch, the realism of found transformations often needs to be traded off against the required runtime. DIR approaches using deep learning (DL) techniques have shown remarkable promise in instantly predicting a transformation. However, on difficult registration problems, the realism of these transformations can fall short. DIR approaches using biomechanical, finite element modeling (FEM) techniques can find more realistic transformations, but tend to require much longer runtimes. This work proposes the first hybrid approach to combine them, with the aim of getting the best of both worlds. This hybrid approach, called DL-MOREA, combines a recently introduced multi-objective DL-based DIR approach which leverages the VoxelMorph framework, called DL-MODIR, with MOREA, an evolutionary algorithm-based, multi-objective DIR approach in which a FEM-like biomechanical mesh transformation model is used. In our proposed hybrid approach, the DL results are used to smartly initialize MOREA, with the aim of more efficiently optimizing its mesh transformation model. We empirically compare DL-MOREA against its components, DL-MODIR and MOREA, on CT scan pairs capturing large bladder filling differences of 15 cervical cancer patients. While MOREA requires a median runtime of 45 minutes, DL-MOREA can already find high-quality transformations after 5 minutes. Compared to the DL-MODIR transformations, the transformations found by DL-MOREA exhibit far less folding and improve or preserve the bladder contour distance error.
Abstract (translated)
在选择用于处理图像变形大且内容不匹配问题的可变形图像配准（DIR）方法时，通常需要权衡变换的真实性和所需运行时间。采用深度学习（DL）技术的DIR方法已显示出能够瞬间预测变换的显著潜力。然而，在困难的注册问题上，这些变换的真实度可能不足。使用生物力学、有限元建模（FEM）技术的DIR方法可以找到更真实的变换，但往往需要更长的运行时间。这项工作提出了首个结合两者的混合方法，旨在获得最佳效果。这种混合方法被命名为DL-MOREA，它将最近引入的一种基于多目标深度学习的DIR方法DL-MODIR（采用VoxelMorph框架）与MOREA相结合，后者是一种基于进化算法的多目标DIR方法，使用类似FEM的生物力学网格变换模型。 在我们提出的混合方法中，DL的结果被用于智能初始化MOREA，旨在更高效地优化其网格变换模型。我们在15名宫颈癌患者的CT扫描对（这些对捕捉了大范围膀胱充盈差异）上将DL-MOREA与其组件DL-MODIR和MOREA进行了实证对比。 与MOREA需要中位运行时间45分钟相比，DL-MOREA能够在短短5分钟后找到高质量的变换。与DL-MODIR发现的变换相比，DL-MOREA所发现的变换表现出更少的折叠现象，并且改善或保持了膀胱轮廓距离误差。
URL
https://arxiv.org/abs/2501.16525
PDF
-
Iterative Shaping of Multi-Particle Aggregates based on Action Trees and VLM
2025-01-23 09:43:16Hoi-Yin Lee, Peng Zhou, Anqing Duan, Chenguang Yang, David Navarro-AlarconAbstract
In this paper, we address the problem of manipulating multi-particle aggregates using a bimanual robotic system. Our approach enables the autonomous transport of dispersed particles through a series of shaping and pushing actions using robotically-controlled tools. Achieving this advanced manipulation capability presents two key challenges: high-level task planning and trajectory execution. For task planning, we leverage Vision Language Models (VLMs) to enable primitive actions such as tool affordance grasping and non-prehensile particle pushing. For trajectory execution, we represent the evolving particle aggregate's contour using truncated Fourier series, providing efficient parametrization of its closed shape. We adaptively compute trajectory waypoints based on group cohesion and the geometric centroid of the aggregate, accounting for its spatial distribution and collective motion. Through real-world experiments, we demonstrate the effectiveness of our methodology in actively shaping and manipulating multi-particle aggregates while maintaining high system cohesion.
Abstract (translated)
在这篇论文中，我们解决了使用双臂机器人系统操控多颗粒集合体的问题。我们的方法通过一系列的塑形和推动动作，实现了分散粒子的自主运输，这些动作是通过机器人力控工具完成的。实现这种高级操作能力面临两大挑战：高层次任务规划和轨迹执行。对于任务规划，我们利用视觉语言模型（VLMs）来启用基本的操作，如工具抓取能力和非抓握式的颗粒推动。在轨迹执行方面，我们使用截断傅里叶级数表示不断变化的颗粒集合体轮廓，从而高效地对其闭合形状进行参数化。根据群体凝聚性和集合体的几何质心自适应计算路径关键点，考虑其空间分布和集体运动。通过真实世界实验，我们证明了我们的方法在主动塑造和操控多颗粒集合体的同时保持系统高凝聚力的有效性。
URL
https://arxiv.org/abs/2501.13507
PDF
-
Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes
2025-01-22 17:52:45Yuang Shi, Simone Gasparini, G\'eraldine Morin, Chenggang Yang, Wei Tsang OoiAbstract
3D Gaussian Splatting (3DGS) has emerged as a promising representation for photorealistic rendering of 3D scenes. However, its high storage requirements pose significant challenges for practical applications. We observe that Gaussians exhibit distinct roles and characteristics that are analogous to traditional artistic techniques -- Like how artists first sketch outlines before filling in broader areas with color, some Gaussians capture high-frequency features like edges and contours; While other Gaussians represent broader, smoother regions, that are analogous to broader brush strokes that add volume and depth to a painting. Based on this observation, we propose a novel hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which define scene boundaries, and (ii) Patch Gaussians, which cover smooth regions. Sketch Gaussians are efficiently encoded using parametric models, leveraging their geometric coherence, while Patch Gaussians undergo optimized pruning, retraining, and vector quantization to maintain volumetric consistency and storage efficiency. Our comprehensive evaluation across diverse indoor and outdoor scenes demonstrates that this structure-aware approach achieves up to 32.62% improvement in PSNR, 19.12% in SSIM, and 45.41% in LPIPS at equivalent model sizes, and correspondingly, for an indoor scene, our model maintains the visual quality with 2.3% of the original model size.
Abstract (translated)
3D高斯点阵（3DGS）作为一种具有前景的表示方法，被应用于三维场景的真实感渲染。然而，其高昂的数据存储需求对实际应用构成了重大挑战。我们观察到，高斯函数在角色和特性上与传统的艺术技巧相似——就像艺术家先勾勒轮廓线再用更宽的笔触填充区域一样，一些高斯函数捕捉了高频特征（如边缘和轮廓），而其他高斯函数则代表更广泛、平滑的区域，类似于为一幅画增加体积感和深度的宽刷子笔触。基于这一观察，我们提出了一种新的混合表示方法，将高斯函数分为两类：(i) 轮廓高斯（Sketch Gaussians），定义场景边界；以及(ii) 补丁高斯（Patch Gaussians），覆盖平滑区域。轮廓高斯通过参数模型进行高效编码，利用其几何一致性，而补丁高斯则经过优化剪枝、重新训练和向量量化处理以保持体积一致性和存储效率。 我们对多种室内及室外场景进行了全面评估，结果表明这种结构感知的方法在等效模型大小下，PSNR（峰值信噪比）提高了多达32.62%，SSIM（结构相似度指数）提升了19.12%，LPIPS（相对图片感知质量评分）减少了45.41%。对于一个室内场景来说，我们的模型可以在仅占原始模型大小的2.3%的情况下保持视觉效果的质量。
URL
https://arxiv.org/abs/2501.13045
PDF
-
GAMED-Snake: Gradient-aware Adaptive Momentum Evolution Deep Snake Model for Multi-organ Segmentation
2025-01-22 12:45:09Ruicheng Zhang, Haowei Guo, Zeyu Zhang, Puxin Yan, Shen ZhaoAbstract
Multi-organ segmentation is a critical yet challenging task due to complex anatomical backgrounds, blurred boundaries, and diverse morphologies. This study introduces the Gradient-aware Adaptive Momentum Evolution Deep Snake (GAMED-Snake) model, which establishes a novel paradigm for contour-based segmentation by integrating gradient-based learning with adaptive momentum evolution mechanisms. The GAMED-Snake model incorporates three major innovations: First, the Distance Energy Map Prior (DEMP) generates a pixel-level force field that effectively attracts contour points towards the true boundaries, even in scenarios with complex backgrounds and blurred edges. Second, the Differential Convolution Inception Module (DCIM) precisely extracts comprehensive energy gradients, significantly enhancing segmentation accuracy. Third, the Adaptive Momentum Evolution Mechanism (AMEM) employs cross-attention to establish dynamic features across different iterations of evolution, enabling precise boundary alignment for diverse morphologies. Experimental results on four challenging multi-organ segmentation datasets demonstrate that GAMED-Snake improves the mDice metric by approximately 2% compared to state-of-the-art methods. Code will be available at this https URL.
Abstract (translated)
多器官分割是一个既关键又具挑战性的任务，原因在于复杂的解剖背景、模糊的边界以及多样化的形态。本研究提出了基于梯度感知自适应动量演化深度蛇（Gradient-aware Adaptive Momentum Evolution Deep Snake, GAMED-Snake）模型，该模型通过将基于梯度的学习与自适应动量演化机制相结合，建立了一种新的轮廓导向分割范式。 GAMED-Snake 模型包含三大创新： 首先，距离能量图先验（Distance Energy Map Prior, DEMP）生成了一个像素级别的力场，能够有效吸引轮廓点向真实的边界靠近，在复杂背景和模糊边缘的情况下效果尤为显著。 其次，差分卷积入模块（Differential Convolution Inception Module, DCIM）可以精确提取全面的能量梯度信息，从而极大地提高了分割的准确性。 第三，自适应动量演化机制（Adaptive Momentum Evolution Mechanism, AMEM）利用跨注意力机制来建立不同进化迭代之间的动态特征，使各种形态下的边界对齐更加精准。 实验结果显示，在四个具有挑战性的多器官分割数据集上，GAMED-Snake 模型相比最先进的方法将 mDice 评价指标提高了约2%。代码将在 [此处](https://example.com) 提供（请使用实际链接）。
URL
https://arxiv.org/abs/2501.12844
PDF
-
Automating High Quality RT Planning at Scale
2025-01-21 00:44:18Riqiang Gao, Mamadou Diallo, Han Liu, Anthony Magliari, Jonathan Sackett, Wilko Verbakel, Sandra Meyers, Masoud Zarepisheh, Rafe Mcbeth, Simon Arberet, Martin Kraus, Florin C. Ghesu, Ali KamenAbstract
Radiotherapy (RT) planning is complex, subjective, and time-intensive. Advances in artificial intelligence (AI) promise to improve its precision, efficiency, and consistency, but progress is often limited by the scarcity of large, standardized datasets. To address this, we introduce the Automated Iterative RT Planning (AIRTP) system, a scalable solution for generating high-quality treatment plans. This scalable solution is designed to generate substantial volumes of consistently high-quality treatment plans, overcoming a key obstacle in the advancement of AI-driven RT planning. Our AIRTP pipeline adheres to clinical guidelines and automates essential steps, including organ-at-risk (OAR) contouring, helper structure creation, beam setup, optimization, and plan quality improvement, using AI integrated with RT planning software like Eclipse of Varian. Furthermore, a novel approach for determining optimization parameters to reproduce 3D dose distributions, i.e. a method to convert dose predictions to deliverable treatment plans constrained by machine limitations. A comparative analysis of plan quality reveals that our automated pipeline produces treatment plans of quality comparable to those generated manually, which traditionally require several hours of labor per plan. Committed to public research, the first data release of our AIRTP pipeline includes nine cohorts covering head-and-neck and lung cancer sites to support an AAPM 2025 challenge. This data set features more than 10 times the number of plans compared to the largest existing well-curated public data set to our best knowledge. Repo:{this https URL}
Abstract (translated)
放射治疗（RT）计划制定是一个复杂、主观且耗时的过程。人工智能（AI）的进步承诺能提高其精确度、效率和一致性，但进展常常受限于大型标准化数据集的稀缺性。为了解决这一问题，我们引入了自动迭代放疗规划（AIRTP）系统，这是一种可扩展解决方案，用于生成高质量治疗计划。该可扩展解决方案旨在产生大量一致且高质量的治疗方案，从而克服AI驱动RT规划中的一大障碍。 我们的AIRTP流程遵循临床指南，并自动化了许多关键步骤，包括风险器官轮廓勾画、辅助结构创建、射束布置、优化和改善计划质量等环节，这些操作通过集成到如Varian公司Eclipse放射治疗软件中的AI技术来实现。此外，我们还提出了一种确定优化参数的方法，以重现三维剂量分布，并将其转换为受机器限制的可实施治疗方案。 在治疗计划的质量比较分析中发现，我们的自动化流程产生的治疗计划质量与手动生成的计划相当，而后者通常需要每份计划数小时的人力劳动。致力于公共研究，我们AIRTP流程的第一个数据发布包括九个队列，涵盖了头颈部和肺癌部位，并支持AAPM 2025挑战赛。此数据集包含的治疗方案数量是我们目前所知的最大、最完善且公开的数据集中同类数据的十倍以上。 相关代码库地址：[点击这里](https://this https URL)（请将URL替换为实际链接）
URL
https://arxiv.org/abs/2501.11803
PDF
-
Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation
2025-01-20 07:23:11Ziheng Zhang, Jianyang Gu, Arpita Chowdhury, Zheda Mai, David Carlyn, Tanya Berger-Wolf, Yu Su, Wei-Lun ChaoAbstract
Class activation map (CAM) has been widely used to highlight image regions that contribute to class predictions. Despite its simplicity and computational efficiency, CAM often struggles to identify discriminative regions that distinguish visually similar fine-grained classes. Prior efforts address this limitation by introducing more sophisticated explanation processes, but at the cost of extra complexity. In this paper, we propose Finer-CAM, a method that retains CAM's efficiency while achieving precise localization of discriminative regions. Our key insight is that the deficiency of CAM lies not in "how" it explains, but in "what" it explains}. Specifically, previous methods attempt to identify all cues contributing to the target class's logit value, which inadvertently also activates regions predictive of visually similar classes. By explicitly comparing the target class with similar classes and spotting their differences, Finer-CAM suppresses features shared with other classes and emphasizes the unique, discriminative details of the target class. Finer-CAM is easy to implement, compatible with various CAM methods, and can be extended to multi-modal models for accurate localization of specific concepts. Additionally, Finer-CAM allows adjustable comparison strength, enabling users to selectively highlight coarse object contours or fine discriminative details. Quantitatively, we show that masking out the top 5% of activated pixels by Finer-CAM results in a larger relative confidence drop compared to baselines. The source code and demo are available at this https URL.
Abstract (translated)
类激活图（Class Activation Map，CAM）广泛用于突出对类别预测有贡献的图像区域。尽管其简单性和计算效率较高，但CAM在识别区分视觉相似的细粒度类别中的判别性区域时常常力不从心。先前的努力通过引入更复杂的解释过程来解决这一限制，但这会增加额外的复杂性。本文中，我们提出了一种名为Finer-CAM的方法，该方法保留了CAM的效率，同时实现了对判别性区域的精确定位。我们的关键见解在于，CAM的不足并不在于它是如何进行解释的，而是在于它所解释的内容。具体而言，先前的方法试图识别所有有助于目标类别logit值的线索，这无意中激活了一些预测视觉相似类别的区域。 通过明确地将目标类别与类似类别进行比较，并找出它们之间的差异，Finer-CAM抑制了与其他类别共享的特征，并强调了目标类别独有的、具有判别性的细节。Finer-CAM易于实现，兼容各种CAM方法，并可以扩展到多模态模型中以准确定位特定概念。此外，Finer-CAM允许调整比较强度，使用户能够选择性地突出粗略的对象轮廓或精细的鉴别性细节。 从定量上看，我们展示了通过Finer-CAM屏蔽激活像素的前5%，相比基线方法会导致相对置信度更大的下降。源代码和演示可在以下链接找到：[请在此处插入URL]。
URL
https://arxiv.org/abs/2501.11309
PDF
-
Hypercone Assisted Contour Generation for Out-of-Distribution Detection
2025-01-17 14:08:32Annita Vapsi, Andr\'es Mu\~noz, Nancy Thomas, Keshav Ramani, Daniel BorrajoAbstract
Recent advances in the field of out-of-distribution (OOD) detection have placed great emphasis on learning better representations suited to this task. While there are distance-based approaches, distributional awareness has seldom been exploited for better performance. We present HAC$_k$-OOD, a novel OOD detection method that makes no distributional assumption about the data, but automatically adapts to its distribution. Specifically, HAC$_k$-OOD constructs a set of hypercones by maximizing the angular distance to neighbors in a given data-point's vicinity to approximate the contour within which in-distribution (ID) data-points lie. Experimental results show state-of-the-art FPR@95 and AUROC performance on Near-OOD detection and on Far-OOD detection on the challenging CIFAR-100 benchmark without explicitly training for OOD performance.
Abstract (translated)
最近在分布外（OOD）检测领域取得的进展，强调了学习更适合该任务的表示方法的重要性。虽然存在基于距离的方法，但分佈感知性很少被利用来提高性能。我们提出了HAC$_k$-OOD，这是一种新颖的OOD检测方法，它不对数据做出任何分布假设，而是自动适应其分布特性。具体来说，HAC$_k$-OOD通过最大化给定点邻域内样本之间的角度距离来构建一组双曲锥体（hypercones），以此近似包含内部分布（ID）数据点的边界轮廓。 实验结果表明，在不特意针对OOD性能进行训练的情况下，HAC$_k$-OOD在Near-OOD检测和具有挑战性的CIFAR-100基准测试中的Far-OOD检测上达到了最先进的FPR@95和AUROC性能。
URL
https://arxiv.org/abs/2501.10209
PDF
