As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for developing new …

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 …

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

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 …

Mining precise class-aware attention maps, aka, class activation maps, is essential for
weakly supervised semantic segmentation. In this paper, we present L2G, a simple online …

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 …

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 …

In this paper, we present a novel cross-consistency based semi-supervised approach for
semantic segmentation. Consistency training has proven to be a powerful semi-supervised …

Camouflage is a key defence mechanism across species that is critical to survival. Common
camouflage include background matching, imitating the color and pattern of the …

Weakly supervised semantic segmentation produces a pixel-level localization from class
labels; but a classifier trained on such labels is likely to restrict its focus to a small …