A Low Rank Promoting Prior for Unsupervised Contrastive Learning

TL;DR

This paper introduces LORAC, a novel contrastive learning framework that incorporates a low rank promoting prior, improving performance across various computer vision tasks by enforcing samples of the same class to lie on a low-dimensional subspace.

Contribution

The paper proposes a probabilistic graphical model with a low rank prior for contrastive learning, explicitly modeling class subspace structures to enhance unsupervised feature learning.

Findings

Outperforms state-of-the-art on image classification benchmarks

Improves object detection and instance segmentation results

Demonstrates the effectiveness of low rank priors in contrastive learning

Abstract

Unsupervised learning is just at a tipping point where it could really take off. Among these approaches, contrastive learning has seen tremendous progress and led to state-of-the-art performance. In this paper, we construct a novel probabilistic graphical model that effectively incorporates the low rank promoting prior into the framework of contrastive learning, referred to as LORAC. In contrast to the existing conventional self-supervised approaches that only considers independent learning, our hypothesis explicitly requires that all the samples belonging to the same instance class lie on the same subspace with small dimension. This heuristic poses particular joint learning constraints to reduce the degree of freedom of the problem during the search of the optimal network parameterization. Most importantly, we argue that the low rank prior employed here is not unique, and many different priors can be invoked in a similar probabilistic way, corresponding to different hypotheses about underlying truth behind the contrastive features. Empirical evidences show that the proposed algorithm clearly surpasses the state-of-the-art approaches on multiple benchmarks, including image classification, object detection, instance segmentation and keypoint detection.