2021/12/21 by Anshul Shah, Suvrit Sra, Shah, Anshul +5 · 6 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Indoor and Outdoor Localization Technologies #Machine Learning (cs.LG) #Sparse and Compressive Sensing Techniques #cs.AI #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2112.11450
Accepted at AAAI 2022
arxiv created 2021/12/21 · openalex publication_date 2021/12/21 · arxiv updated 2021/12/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.