Saved in:
Bibliographic Details
Main Authors: Li, Chengtai, He, Yuting, Ren, Jianfeng, Bai, Ruibin, Zhao, Yitian, Yu, Heng, Jiang, Xudong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.01125
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912934769197056
author Li, Chengtai
He, Yuting
Ren, Jianfeng
Bai, Ruibin
Zhao, Yitian
Yu, Heng
Jiang, Xudong
author_facet Li, Chengtai
He, Yuting
Ren, Jianfeng
Bai, Ruibin
Zhao, Yitian
Yu, Heng
Jiang, Xudong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01125
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Predictive Reasoning with Augmented Anomaly Contrastive Learning for Compositional Visual Relations
Li, Chengtai
He, Yuting
Ren, Jianfeng
Bai, Ruibin
Zhao, Yitian
Yu, Heng
Jiang, Xudong
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Predictive Reasoning with Augmented Anomaly Contrastive Learning for Compositional Visual Relations
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.01125