K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
This addresses the challenge of improving unsupervised visual representation learning for computer vision tasks, though it appears incremental as it generalizes existing contrastive learning methods.
The paper tackles the problem of learning visual features by proposing K-Shot Contrastive Learning (KSCL), which uses multiple augmentations per instance to model intra-instance variations and inter-instance discrimination, achieving superior performance over state-of-the-art unsupervised methods.
In this paper, we propose the $K$-Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances. It aims to combine the advantages of inter-instance discrimination by learning discriminative features to distinguish between different instances, as well as intra-instance variations by matching queries against the variants of augmented samples over instances. Particularly, for each instance, it constructs an instance subspace to model the configuration of how the significant factors of variations in $K$-shot augmentations can be combined to form the variants of augmentations. Given a query, the most relevant variant of instances is then retrieved by projecting the query onto their subspaces to predict the positive instance class. This generalizes the existing contrastive learning that can be viewed as a special one-shot case. An eigenvalue decomposition is performed to configure instance subspaces, and the embedding network can be trained end-to-end through the differentiable subspace configuration. Experiment results demonstrate the proposed $K$-shot contrastive learning achieves superior performances to the state-of-the-art unsupervised methods.