Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection

TL;DR

This paper introduces PixTrace and CopyNCE to improve image copy detection by maintaining pixel-level spatial mappings and regularizing patch similarity, achieving state-of-the-art results and enhanced interpretability.

Contribution

The paper presents a novel pixel coordinate tracking module and a geometrically-guided contrastive loss to enhance fine-grained correspondence learning in copy detection.

Findings

Achieves state-of-the-art performance on DISC21 dataset.

Improves interpretability of copy detection methods.

Effectively suppresses supervision noise in SSL training.

Abstract

Image Copy Detection (ICD) aims to identify manipulated content between image pairs through robust feature representation learning. While self-supervised learning (SSL) has advanced ICD systems, existing view-level contrastive methods struggle with sophisticated edits due to insufficient fine-grained correspondence learning. We address this limitation by exploiting the inherent geometric traceability in edited content through two key innovations. First, we propose PixTrace - a pixel coordinate tracking module that maintains explicit spatial mappings across editing transformations. Second, we introduce CopyNCE, a geometrically-guided contrastive loss that regularizes patch affinity using overlap ratios derived from PixTrace's verified mappings. Our method bridges pixel-level traceability with patch-level similarity learning, suppressing supervision noise in SSL training. Extensive experiments demonstrate not only state-of-the-art performance (88.7% uAP / 83.9% RP90 for matcher, 72.6% uAP / 68.4% RP90 for descriptor on DISC21 dataset) but also better interpretability over existing methods.