Review the state-of-the-art technologies of semantic segmentation based on deep learning
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 …
information and predict the semantic category of each pixel from a given label set. With the …
A survey on label-efficient deep image segmentation: Bridging the gap between weak supervision and dense prediction
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 …
one of the fundamental tasks of computer vision. However, the current segmentation …
Multi-class token transformer for weakly supervised semantic 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) …
localization maps as pseudo labels for weakly supervised semantic segmentation (WSSS) …
Learning affinity from attention: End-to-end weakly-supervised semantic segmentation with transformers
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 …
and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS …
Class re-activation maps for weakly-supervised semantic segmentation
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 …
pseudo masks for weakly-supervised semantic segmentation (WSSS). Yet, we find that the …
Regional semantic contrast and aggregation for weakly supervised semantic segmentation
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 …
challenging since it is hard to infer dense object regions from sparse semantic tags. Despite …
Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation
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 …
has attracted much attention due to low annotation costs. Existing methods often rely on …
Long-tailed classification by keeping the good and removing the bad momentum causal effect
As the class size grows, maintaining a balanced dataset across many classes is challenging
because the data are long-tailed in nature; it is even impossible when the sample-of-interest …
because the data are long-tailed in nature; it is even impossible when the sample-of-interest …
Clims: Cross language image matching for weakly supervised semantic segmentation
It has been widely known that CAM (Class Activation Map) usually only activates
discriminative object regions and falsely includes lots of object-related backgrounds. As only …
discriminative object regions and falsely includes lots of object-related backgrounds. As only …
Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation
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 …
labels; but a classifier trained on such labels is likely to restrict its focus to a small …