Weakly Supervised Contrastive Learning
This work addresses a key limitation in self-supervised learning for computer vision, offering improved representation quality that benefits tasks like semi-supervised learning, though it is incremental in building on existing contrastive methods.
The paper tackles the class collision problem in unsupervised contrastive learning by introducing a weakly supervised framework (WCL) that uses a graph-based method to generate weak labels and a multi-crop strategy, achieving 65% and 72% ImageNet Top-1 Accuracy with 1% and 10% labeled data using ResNet50, which surpasses prior state-of-the-art results.
Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance discrimination as the pretext task, which treating every single instance as a different class. However, such method will inevitably cause class collision problems, which hurts the quality of the learned representation. Motivated by this observation, we introduced a weakly supervised contrastive learning framework (WCL) to tackle this issue. Specifically, our proposed framework is based on two projection heads, one of which will perform the regular instance discrimination task. The other head will use a graph-based method to explore similar samples and generate a weak label, then perform a supervised contrastive learning task based on the weak label to pull the similar images closer. We further introduced a K-Nearest Neighbor based multi-crop strategy to expand the number of positive samples. Extensive experimental results demonstrate WCL improves the quality of self-supervised representations across different datasets. Notably, we get a new state-of-the-art result for semi-supervised learning. With only 1\% and 10\% labeled examples, WCL achieves 65\% and 72\% ImageNet Top-1 Accuracy using ResNet50, which is even higher than SimCLRv2 with ResNet101.