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 …
Unsupervised semantic segmentation by contrasting object mask proposals
Being able to learn dense semantic representations of images without supervision is an
important problem in computer vision. However, despite its significance, this problem …
important problem in computer vision. However, despite its significance, this problem …
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 …
Semi-supervised semantic segmentation with directional context-aware consistency
Semantic segmentation has made tremendous progress in recent years. However, satisfying
performance highly depends on a large number of pixel-level annotations. Therefore, in this …
performance highly depends on a large number of pixel-level annotations. Therefore, in this …
Reducing information bottleneck for weakly supervised semantic segmentation
Weakly supervised semantic segmentation produces pixel-level localization from class
labels; however, a classifier trained on such labels is likely to focus on a small discriminative …
labels; however, a classifier trained on such labels is likely to focus on a small discriminative …
Sg-one: Similarity guidance network for one-shot semantic segmentation
One-shot image semantic segmentation poses a challenging task of recognizing the object
regions from unseen categories with only one annotated example as supervision. In this …
regions from unseen categories with only one annotated example as supervision. In this …
Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation
Semantic segmentation is a challenging task in the absence of densely labelled data. Only
relying on class activation maps (CAM) with image-level labels provides deficient …
relying on class activation maps (CAM) with image-level labels provides deficient …
Unsupervised learning of image segmentation based on differentiable feature clustering
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation
was investigated in this study. Similar to supervised image segmentation, the proposed CNN …
was investigated in this study. Similar to supervised image segmentation, the proposed CNN …
Bbam: Bounding box attribution map for weakly supervised semantic and instance segmentation
Weakly supervised segmentation methods using bounding box annotations focus on
obtaining a pixel-level mask from each box containing an object. Existing methods typically …
obtaining a pixel-level mask from each box containing an object. Existing methods typically …