Abstract For Weakly-Supervised Semantic Segmentation (WSSS) with image-level
annotation, mostly relies on the classification network to generate initial segmentation …

We address the problem of weakly-supervised semantic segmentation (WSSS) using
bounding box annotations. Although object bounding boxes are good indicators to segment …

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 …

Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level
weak supervision have several limitations: sparse object coverage, inaccurate object …

Image-level weakly-supervised semantic segmentation (WSSS) aims at learning semantic
segmentation by adopting only image class labels. Existing approaches generally rely on …

In this work, we propose a new transformer-based regularization to better localize objects for
Weakly supervised semantic segmentation (WSSS). In image-level WSSS, Class Activation …

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

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

Weakly supervised semantic segmentation has witnessed great achievements with image-
level labels. Several recent approaches use the CLIP model to generate pseudo labels for …

Abstract Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels
has been greatly advanced by exploiting the outputs of Class Activation Map (CAM) to …