The goal of semantic segmentation is to segment the input image according to semantic
information and predict the semantic category of each pixel from a given label set. With the …

Deep semi-supervised learning is a fast-growing field with a range of practical applications.
This paper provides a comprehensive survey on both fundamentals and recent advances in …

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 …

Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important
and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS …

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 …

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 …

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 …

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 …

Being able to learn dense semantic representations of images without supervision is an
important problem in computer vision. However, despite its significance, this problem …

Despite the great progress made by deep CNNs in image semantic segmentation, they
typically require a large number of densely-annotated images for training and are difficult to …