Self-Supervised Class-Cognizant Few-Shot Classification
This work addresses the challenge of learning from unlabeled data for few-shot classification, which is important for AI systems with limited labeled data, but it appears incremental as it extends existing contrastive learning approaches.
The paper tackles the problem of few-shot classification by proposing a self-supervised pre-training method with class-level cognizance, achieving new state-of-the-art results on standard mini-ImageNet and cross-domain CDFSL benchmarks.
Unsupervised learning is argued to be the dark matter of human intelligence. To build in this direction, this paper focuses on unsupervised learning from an abundance of unlabeled data followed by few-shot fine-tuning on a downstream classification task. To this aim, we extend a recent study on adopting contrastive learning for self-supervised pre-training by incorporating class-level cognizance through iterative clustering and re-ranking and by expanding the contrastive optimization loss to account for it. To our knowledge, our experimentation both in standard and cross-domain scenarios demonstrate that we set a new state-of-the-art (SoTA) in (5-way, 1 and 5-shot) settings of standard mini-ImageNet benchmark as well as the (5-way, 5 and 20-shot) settings of cross-domain CDFSL benchmark. Our code and experimentation can be found in our GitHub repository: https://github.com/ojss/c3lr.