Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning

TL;DR

This paper introduces IMSVD, a novel self-supervised learning method that discretizes latent variables to improve image representation learning, achieving better accuracy, efficiency, and explainability over existing methods.

Contribution

The paper presents IMSVD, a new SSL approach that softly discretizes latent variables and uses an information-theoretic objective, outperforming prior contrastive and non-contrastive methods.

Findings

IMSVD improves downstream task accuracy.

IMSVD enhances learning efficiency.

Features offer variable-level explainability.

Abstract

Self-supervised learning (SSL) has emerged as a crucial technique in image processing, encoding, and understanding, especially for developing today's vision foundation models that utilize large-scale datasets without annotations to enhance various downstream tasks. This study introduces a novel SSL approach, Information-Maximized Soft Variable Discretization (IMSVD), for image representation learning. Specifically, IMSVD softly discretizes each variable in the latent space, enabling the estimation of their probability distributions over training batches and allowing the learning process to be directly guided by information measures. Motivated by the MultiView assumption, we propose an information-theoretic objective function to learn transform-invariant, non-travail, and redundancy-minimized representation features. We then derive a joint-cross entropy loss function for self-supervised image representation learning, which theoretically enjoys superiority over the existing methods in reducing feature redundancy. Notably, our non-contrastive IMSVD method statistically performs contrastive learning. Extensive experimental results demonstrate the effectiveness of IMSVD on various downstream tasks in terms of both accuracy and efficiency. Thanks to our variable discretization, the embedding features optimized by IMSVD offer unique explainability at the variable level. IMSVD has the potential to be adapted to other learning paradigms. Our code is publicly available at https://github.com/niuchuangnn/IMSVD.