Max-Margin Contrastive Learning
This work addresses a bottleneck in unsupervised representation learning for computer vision, offering an incremental improvement over existing methods.
The paper tackles the problem of slow convergence and the need for many negatives in contrastive learning by proposing max-margin contrastive learning (MMCL), which selects negatives as sparse support vectors via quadratic optimization to maximize the decision margin, resulting in better performance and convergence on standard vision benchmarks.
Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence. We suspect this behavior is due to the suboptimal selection of negatives used for offering contrast to the positives. We counter this difficulty by taking inspiration from support vector machines (SVMs) to present max-margin contrastive learning (MMCL). Our approach selects negatives as the sparse support vectors obtained via a quadratic optimization problem, and contrastiveness is enforced by maximizing the decision margin. As SVM optimization can be computationally demanding, especially in an end-to-end setting, we present simplifications that alleviate the computational burden. We validate our approach on standard vision benchmark datasets, demonstrating better performance in unsupervised representation learning over state-of-the-art, while having better empirical convergence properties.