Colour augmentation for improved semi-supervised semantic segmentation
Not on the map. Why?
Abstract (arXiv)
Consistency regularization describes a class of approaches that have yielded state-of-the-art results for semi-supervised classification. While semi-supervised semantic segmentation proved to be more challenging, a number of successful approaches have been recently proposed. Recent work explored the challenges involved in using consistency regularization for segmentation problems. In their self-supervised work Chen et al. found that colour augmentation prevents a classification network from using image colour statistics as a short-cut for self-supervised learning via instance discrimination. Drawing inspiration from this we find that a similar problem impedes semi-supervised semantic segmentation and offer colour augmentation as a solution, improving semi-supervised semantic segmentation performance on challenging photographic imagery.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 35 references that are in the map. First posted on arXiv 9 Oct 2021.
Builds on
27 of 35 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
- 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
- 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
- 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
- 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
- 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
15 more
- 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
- 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
- 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 248
- 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
- 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
- 2016Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)cited by 197
- 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
- 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
- 2017Deep Extreme Cut: From Extreme Points to Object Segmentationcited by 127
- 2021Bootstrapping Semantic Segmentation with Regional Contrastcited by 80
- 2020DMT: Dynamic Mutual Training for Semi-Supervised Learningcited by 77
- 2017Smooth Neighbors on Teacher Graphs for Semi-supervised Learningcited by 48
- 2018Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Modelcited by 45
- 2016Mutual Exclusivity Loss for Semi-Supervised Deep Learningcited by 22
- 2018Deep semi-supervised segmentation with weight-averaged consistency targetscited by 21
Built on by
Citing papers per year: 2023: 2.
2 papers.