3 papers
cs.CV2024
Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation
Wangyu Wu, Tianhong Dai, Zhenhong Chen +4
Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to its cost-effectiveness. The typical framework involves using im…
cs.CV2023
Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation
Wangyu Wu, Tianhong Dai, Xiaowei Huang +2
Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to cost-effectiveness. Recently, Vision Transformer (ViT) based me…
cs.CV2023
Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation
Wangyu Wu, Tianhong Dai, Xiaowei Huang +2
Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primar…