论文标题
基于注意力的班级激活扩散，用于弱监督语义分割
Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation
论文作者
论文摘要
提取类激活图（CAM）是弱监督语义分割（WSSS）的关键步骤。卷积神经网络的凸轮无法捕获对图像的远程功能的依赖，并仅在前景对象部分（即许多错误的负面因素）上覆盖。 An intuitive solution is ``coupling'' the CAM with the long-range attention matrix of visual transformers (ViT) We find that the direct ``coupling'', e.g., pixel-wise multiplication of attention and activation, achieves a more global coverage (on the foreground), but unfortunately goes with a great increase of false positives, i.e., background pixels are mistakenly included.本文旨在解决此问题。它提出了一种新方法，以概率扩散方式将CAM和注意力矩阵搭配，然后将其配置为AD-CAM。直观地，它以保守而令人信服的方式整合了VIT的关注和CAM激活。保守的是通过基于对普通邻居的注意力来提高一对像素之间的注意力，在这些像素之间，直觉是两个具有非常不同社区的像素很少被依赖的像素，即应减少他们的注意力。通过将像素的激活扩散到其邻居（在CAM上）（在AM上）成比例，可以实现令人信服的。在实验中，我们对两个具有挑战性的WSS基准Pascal VOC和MS〜可可的结果表明，AD-CAM作为伪标签可以产生比CAM的最先进变体产生更强的WSSSS模型。
Extracting class activation maps (CAM) is a key step for weakly-supervised semantic segmentation (WSSS). The CAM of convolution neural networks fails to capture long-range feature dependency on the image and result in the coverage on only foreground object parts, i.e., a lot of false negatives. An intuitive solution is ``coupling'' the CAM with the long-range attention matrix of visual transformers (ViT) We find that the direct ``coupling'', e.g., pixel-wise multiplication of attention and activation, achieves a more global coverage (on the foreground), but unfortunately goes with a great increase of false positives, i.e., background pixels are mistakenly included. This paper aims to tackle this issue. It proposes a new method to couple CAM and Attention matrix in a probabilistic Diffusion way, and dub it AD-CAM. Intuitively, it integrates ViT attention and CAM activation in a conservative and convincing way. Conservative is achieved by refining the attention between a pair of pixels based on their respective attentions to common neighbors, where the intuition is two pixels having very different neighborhoods are rarely dependent, i.e., their attention should be reduced. Convincing is achieved by diffusing a pixel's activation to its neighbors (on the CAM) in proportion to the corresponding attentions (on the AM). In experiments, our results on two challenging WSSS benchmarks PASCAL VOC and MS~COCO show that AD-CAM as pseudo labels can yield stronger WSSS models than the state-of-the-art variants of CAM.
