Predictive Reasoning with Augmented Anomaly Contrastive Learning for Compositional Visual Relations

TL;DR

This paper introduces PR-A$^2$CL, a novel framework for compositional visual reasoning that combines anomaly contrastive learning with a predict-and-verify paradigm, significantly improving performance on complex CVR tasks.

Contribution

The paper proposes a new method integrating augmented anomaly contrastive learning with a rule-based reasoning paradigm for better compositional visual relation understanding.

Findings

Outperforms state-of-the-art models on SVRT, CVR, and MC$^2$R datasets.

Effectively models complex compositional rules.

Enhances generalization in visual reasoning tasks.

Abstract

While visual reasoning for simple analogies has received significant attention, compositional visual relations (CVR) remain relatively unexplored due to their greater complexity. To solve CVR tasks, we propose Predictive Reasoning with Augmented Anomaly Contrastive Learning (PR-A$^2$CL), \ie, to identify an outlier image given three other images that follow the same compositional rules. To address the challenge of modelling abundant compositional rules, an Augmented Anomaly Contrastive Learning is designed to distil discriminative and generalizable features by maximizing similarity among normal instances while minimizing similarity between normal and anomalous outliers. More importantly, a predict-and-verify paradigm is introduced for rule-based reasoning, in which a series of Predictive Anomaly Reasoning Blocks (PARBs) iteratively leverage features from three out of the four images to predict those of the remaining one. Throughout the subsequent verification stage, the PARBs progressively pinpoint the specific discrepancies attributable to the underlying rules. Experimental results on SVRT, CVR and MC$^2$R datasets show that PR-A$^2$CL significantly outperforms state-of-the-art reasoning models.