通过蒸馏邻近模式实现多级标签校正的半监督语义分割
Multi-Level Label Correction by Distilling Proximate Patterns for Semi-supervised Semantic Segmentation
AI总结：
针对半监督语义分割中伪标签不可靠的问题，提出MLLC算法，利用语义级和类别级图的邻近模式纠正错误伪标签，并在多个基准上取得最优性能。
摘要：
半监督语义分割通过利用未标记数据缓解了对大规模标记数据的依赖。近期的半监督语义分割方法主要借助伪标签方法来开发未标记数据。然而，不可靠的伪标签会破坏半监督过程。本文提出一种名为多级标签校正（MLLC）的算法，旨在利用图神经网络捕获语义级图（SLG）和类别级图（CLG）中的结构关系，以纠正错误的伪标签。具体而言，SLG表示像素特征对之间的语义亲和性，而CLG描述像素标签对之间的分类一致性。在来自图的邻近模式信息支持下，MLLC能够纠正预测错误的伪标签，并促进具有判别性的特征表示。我们设计了一个端到端网络来训练并执行这一有效的标签校正机制。实验表明，MLLC能够显著提升监督基线，并在Cityscapes和PASCAL VOC 2012数据集的不同场景中优于现有最先进方法。具体而言，在不同划分协议下，MLLC结合DeepLabV2和DeepLabV3+分别将监督基线至少提升5%和2%。
英文摘要：
Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled data. However, unreliable pseudo-labeling can undermine the semi-supervision processes. In this paper, we propose an algorithm called Multi-Level Label Correction (MLLC), which aims to use graph neural networks to capture structural relationships in Semantic-Level Graphs (SLGs) and Class-Level Graphs (CLGs) to rectify erroneous pseudo-labels. Specifically, SLGs represent semantic affinities between pairs of pixel features, and CLGs describe classification consistencies between pairs of pixel labels. With the support of proximate pattern information from graphs, MLLC can rectify incorrectly predicted pseudo-labels and can facilitate discriminative feature representations. We design an end-to-end network to train and perform this effective label corrections mechanism. Experiments demonstrate that MLLC can significantly improve supervised baselines and outperforms state-of-the-art approaches in different scenarios on Cityscapes and PASCAL VOC 2012 datasets. Specifically, MLLC improves the supervised baseline by at least 5% and 2% with DeepLabV2 and DeepLabV3+ respectively under different partition protocols.
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。
