Bootstrapping Semantic Segmentation with Regional Contrast

By Shikun Liu, Shuaifeng Zhi, Edward Johns, Andrew J. Davison. 2021

159 citations recorded by the source corpus.

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative pixels, with minimal additional memory footprint. ReCo is easy to implement, being built on top of off-the-shelf segmentation networks, and consistently improves performance in both semi-supervised and supervised semantic segmentation methods, achieving smoother segmentation boundaries and faster convergence. The strongest effect is in semi-supervised learning with very few labels. With ReCo, we achieve high-quality semantic segmentation models, requiring only 5 examples of each semantic class. Code is available at https://github.com/lorenmt/reco.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Rui Zhao
2. Wayne Zhang
3. Lei Qi
4. Xinyi Le
5. Lihe Yang
6. Yujun Shen
7. Litong Feng
8. Haochen Wang

In Computer Vision and Pattern Recognition

1. Wayne Zhang
2. Yujun Shen
3. Rui Zhao
4. Lei Qi
5. Xinyi Le
6. Lihe Yang
7. Yuchao Wang
8. Guoqiang Jin

In Representation & Self-Supervised Learning

1. Rui Zhao
2. Wayne Zhang
3. Lei Qi
4. Xinyi Le
5. Lihe Yang
6. Yuchao Wang
7. Yujun Shen
8. Guoqiang Jin

Citations in the corpus

• Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation (2022, methodology): “Motivated by the rapid progress in SSL, recent methods [49, 18, 32, 46, 81, 79, 78, 1, 75, 40, 42, 34, 74] strive for simpler training paradigms from the perspective of consistency regularization and entropy minimization.”
• Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels (2022, background): “In semantic segmentation, contrastive learning has become a promising new paradigm [1,29,41,48,50].”