Contrastive Learning With Stronger Augmentations

By Xiao Wang, Guo-Jun Qi. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021

326 citations recorded by the source corpus.

Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods are benefited from various data augmentations that are carefully designated to maintain their identities so that the images transformed from the same instance can still be retrieved. However, those carefully designed transformations limited us to further explore the novel patterns exposed by other transformations. Meanwhile, as shown in our experiments, direct contrastive learning for stronger augmented images can not learn representations effectively. Thus, we propose a general framework called Contrastive Learning with Stronger Augmentations (CLSA) to complement current contrastive learning approaches. Here, the distribution divergence between the weakly and strongly augmented images over the representation bank is adopted to supervise the retrieval of strongly augmented queries from a pool of instances. Experiments on the ImageNet dataset and downstream datasets showed the information from the strongly augmented images can significantly boost the performance. For example, CLSA achieves top-1 accuracy of 76.2% on ImageNet with a standard ResNet-50 architecture with a single-layer classifier fine-tuned, which is almost the same level as 76.5% of supervised results.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/97ff9cbfe1ea281da48361fa0eea73bd19258980

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. Chuan Zhou
2. Philip S. Yu
3. Feng Xia
4. Shirui Pan
5. Yixin Liu
6. Ming Jin
7. Charu C. Aggarwal
8. Bing Liu

In Computer Vision and Pattern Recognition

1. Shirui Pan
2. Chuan Zhou
3. Philip S. Yu
4. Ming Jin
5. Yixin Liu
6. Feng Xia
7. Charu C. Aggarwal
8. Dacheng Tao

Citations in the corpus

• Graph Self-Supervised Learning: A Survey (2021, background): “To bridge the gaps, adaptively performing graph augmentations [69], automatically selecting augmentations [70] or jointly considering stronger augmented samples [67] by mining the rich underlying structural and attributive information would be interesting directions for further investigation.”