利用序列先验校正噪声标签：面向鲁棒视频分割的多尺度时序特征亲和性学习
Rectifying Noisy Labels with Sequential Prior: Multi-Scale Temporal Feature Affinity Learning for Robust Video Segmentation
AI总结：
本文提出MS-TFAL框架，利用相邻帧时序特征亲和性识别噪声标签，并通过视频、图像、像素三尺度重加权与精炼监督，提升噪声标签医学视频分割的鲁棒性。
摘要：
噪声标签问题不可避免地存在于医学图像分割中，并导致严重的性能下降。以往针对噪声标签问题的分割方法仅利用单张图像，而利用图像间相关性的潜力被忽视。尤其对于视频分割，相邻帧包含丰富的上下文信息，有助于识别噪声标签。基于两点认识，我们提出了一个多尺度时序特征亲和性学习（MS-TFAL）框架，以解决带噪声标签的医学视频分割问题。首先，我们认为视频的序列先验是一种有效参考，即来自相邻帧的像素级特征对于同一类别在距离上相近，而对于不同类别则相距较远。因此，我们设计了时序特征亲和性学习（TFAL），通过评估两个相邻帧中像素之间的亲和性来指示可能的噪声标签。我们还注意到，噪声分布在视频、图像和像素层面表现出相当大的差异。据此，我们引入多尺度监督（MSS），通过对样本重新加权和精炼，从三个不同视角监督网络。该设计使网络能够以由粗到细的方式专注于干净样本。在合成标签噪声和真实世界标签噪声上的实验均表明，我们的方法优于近期最先进的鲁棒分割方法。代码可在 https://github.com/BeileiCui/MS-TFAL 获取。
英文摘要：
Noisy label problems are inevitably in existence within medical image segmentation causing severe performance degradation. Previous segmentation methods for noisy label problems only utilize a single image while the potential of leveraging the correlation between images has been overlooked. Especially for video segmentation, adjacent frames contain rich contextual information beneficial in cognizing noisy labels. Based on two insights, we propose a Multi-Scale Temporal Feature Affinity Learning (MS-TFAL) framework to resolve noisy-labeled medical video segmentation issues. First, we argue the sequential prior of videos is an effective reference, i.e., pixel-level features from adjacent frames are close in distance for the same class and far in distance otherwise. Therefore, Temporal Feature Affinity Learning (TFAL) is devised to indicate possible noisy labels by evaluating the affinity between pixels in two adjacent frames. We also notice that the noise distribution exhibits considerable variations across video, image, and pixel levels. In this way, we introduce Multi-Scale Supervision (MSS) to supervise the network from three different perspectives by re-weighting and refining the samples. This design enables the network to concentrate on clean samples in a coarse-to-fine manner. Experiments with both synthetic and real-world label noise demonstrate that our method outperforms recent state-of-the-art robust segmentation approaches. Code is available at https://github.com/BeileiCui/MS-TFAL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
