Background Noise Reduction of Attention Map for Weakly Supervised Semantic Segmentation

arXiv:2404.03394v1 Announce Type: new
Abstract: In weakly-supervised semantic segmentation (WSSS) using only image-level class labels, a problem with CNN-based Class Activation Maps (CAM) is that they tend to activate the most discriminative local regions of objects. On the other hand, methods based on Transformers learn global features but suffer from the issue of background noise contamination. This paper focuses on addressing the issue of background noise in attention weights within the existing WSSS method based on Conformer, known as TransCAM. …

abstract arxiv attention class cnn cs.cv features global image labels learn map maps noise objects segmentation semantic transformers type weakly-supervised