论文标题
避免纠正措施，以进行弱监督的语义细分
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
论文作者
论文摘要
弱监督的语义分割通常受到类激活图的启发，该图像是伪造的伪造面具，并强调了歧视区域。尽管已经做出了巨大的努力来回顾每个类别的精确和完整的位置，但现有的方法仍然通常遭受不属于标签候选者的未经请求的未经请求的错误预测（OC）错误预测，这是可以避免的，因为很容易被检测到与图像级类标签的矛盾。在本文中，我们以插件方式开发了一种基于组排名的偏置整流（OCR）机制。首先，我们根据其先前的注释相关性和后验预测相关性，将语义类别自适应地将语义类别分为候选（IC）和OC组。然后，我们得出了可区分的整流损失，以迫使OC像素转移到IC组。将我们的OCR与开启基线（例如AffinityNet，接缝，mctformer）结合在一起，我们可以在Pascal VOC（ +3.2％， +3.2％， +3.3％， +0.8％MIOU）和MS COCO（ +1.0％， +1.0％， +1.3％， +1.3％， +1.3％， +0.5％MIOU）的数据上取得显着的效果，并随身携带额外培训。
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although tremendous efforts have been made to recall precise and complete locations for each class, existing methods still commonly suffer from the unsolicited Out-of-Candidate (OC) error predictions that not belongs to the label candidates, which could be avoidable since the contradiction with image-level class tags is easy to be detected. In this paper, we develop a group ranking-based Out-of-Candidate Rectification (OCR) mechanism in a plug-and-play fashion. Firstly, we adaptively split the semantic categories into In-Candidate (IC) and OC groups for each OC pixel according to their prior annotation correlation and posterior prediction correlation. Then, we derive a differentiable rectification loss to force OC pixels to shift to the IC group. Incorporating our OCR with seminal baselines (e.g., AffinityNet, SEAM, MCTformer), we can achieve remarkable performance gains on both Pascal VOC (+3.2%, +3.3%, +0.8% mIoU) and MS COCO (+1.0%, +1.3%, +0.5% mIoU) datasets with negligible extra training overhead, which justifies the effectiveness and generality of our OCR.
