Review the state-of-the-art technologies of semantic segmentation based on deep learning

Y Mo, Y Wu, X Yang, F Liu, Y Liao - Neurocomputing, 2022 - Elsevier
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 …

A survey on label-efficient deep image segmentation: Bridging the gap between weak supervision and dense prediction

W Shen, Z Peng, X Wang, H Wang… - IEEE transactions on …, 2023 - ieeexplore.ieee.org
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 …

Unsupervised semantic segmentation by contrasting object mask proposals

W Van Gansbeke, S Vandenhende… - Proceedings of the …, 2021 - openaccess.thecvf.com
Being able to learn dense semantic representations of images without supervision is an
important problem in computer vision. However, despite its significance, this problem …

Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation

J Lee, E Kim, S Yoon - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
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 …

Reducing information bottleneck for weakly supervised semantic segmentation

J Lee, J Choi, J Mok, S Yoon - Advances in neural …, 2021 - proceedings.neurips.cc
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 …

Semi-supervised semantic segmentation with directional context-aware consistency

X Lai, Z Tian, L Jiang, S Liu, H Zhao… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation

L Xu, W Ouyang, M Bennamoun… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

Weakly supervised segmentation of COVID19 infection with scribble annotation on CT images

X Liu, Q Yuan, Y Gao, K He, S Wang, X Tang, J Tang… - Pattern recognition, 2022 - Elsevier
Segmentation of infections from CT scans is important for accurate diagnosis and follow-up
in tackling the COVID-19. Although the convolutional neural network has great potential to …

Unsupervised learning of image segmentation based on differentiable feature clustering

W Kim, A Kanezaki, M Tanaka - IEEE Transactions on Image …, 2020 - ieeexplore.ieee.org
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation
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

J Lee, J Yi, C Shin, S Yoon - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Weakly supervised segmentation methods using bounding box annotations focus on
obtaining a pixel-level mask from each box containing an object. Existing methods typically …