Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations

TL;DR

This paper introduces a visual probing framework inspired by NLP techniques to explain self-supervised image representations by analyzing semantic relationships and visual analogs, enhancing interpretability of these models.

Contribution

It proposes a systematic approach to create visual language analogs for explaining self-supervised image models, grounded in Marr's vision theory, bridging NLP and computer vision interpretability.

Findings

Relations between language and vision aid in understanding models

Visual words and taxonomy help explain features like textures and shapes

The framework demonstrates effectiveness in interpreting self-supervised representations

Abstract

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind. Motivated by this observation, we introduce a novel visual probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing. The probing tasks require knowledge about semantic relationships between image parts. Hence, we propose a systematic approach to obtain analogs of natural language in vision, such as visual words, context, and taxonomy. Our proposal is grounded in Marr's computational theory of vision and concerns features like textures, shapes, and lines. We show the effectiveness and applicability of those analogs in the context of explaining self-supervised representations. Our key findings emphasize that relations between language and vision can serve as an effective yet intuitive tool for discovering how machine learning models work, independently of data modality. Our work opens a plethora of research pathways towards more explainable and transparent AI.