The rapid development of deep learning has made a great progress in image segmentation,
one of the fundamental tasks of computer vision. However, the current segmentation …

The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Fully convolutional neural networks (FCNs) have shown their advantages in the salient
object detection task. However, most existing FCNs-based methods still suffer from coarse …

This paper proposes a new transformer-based framework to learn class-specific object
localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS) …

Image-level weakly supervised semantic segmentation is a challenging problem that has
been deeply studied in recent years. Most of advanced solutions exploit class activation map …

The task of semantic segmentation holds a fundamental position in the field of computer
vision. Assigning a semantic label to each pixel in an image is a challenging task. In recent …

Extracting class activation maps (CAM) is arguably the most standard step of generating
pseudo masks for weakly-supervised semantic segmentation (WSSS). Yet, we find that the …

Learning semantic segmentation from weakly-labeled (eg, image tags only) data is
challenging since it is hard to infer dense object regions from sparse semantic tags. Despite …

Abstract Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels
has attracted much attention due to low annotation costs. Existing methods often rely on …

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of
consistency regularization and pseudo-labeling can effectively improve image classification …