We present a causal inference framework to improve Weakly-Supervised Semantic
Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by …

Generating precise class-aware pseudo ground-truths, aka, class activation maps (CAMs), is
essential for Weakly-Supervised Semantic Segmentation. The original CAM method usually …

Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that
generates pseudo-masks initially and trains the segmentation model with the pseudo-masks …

Image-level label based weakly-supervised semantic segmentation (WSSS) aims to adopt
image-level labels to train semantic segmentation models, saving vast human labors for …

Data augmentation is vital for deep learning neural networks. By providing massive training
samples, it helps to improve the generalization ability of the model. Weakly supervised …

Seed area generation is usually the starting point of weakly supervised semantic
segmentation (WSSS). Computing the Class Activation Map (CAM) from a multi-label …

Abstract In Weakly Supervised Semantic Segmentation (WSSS), Class Activation Maps
(CAMs) usually 1) do not cover the whole object and 2) be activated on irrelevant regions …

Weakly-supervised semantic segmentation (WSSS) using image-level labels has recently
attracted much attention for reducing annotation costs. Existing WSSS methods utilize …

Efficiently training accurate deep models for weakly supervised semantic segmentation
(WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS …

Weakly-supervised semantic segmentation (WSSS) methods with image-level labels
generally train a classification network to generate the Class Activation Maps (CAMs) as the …