NCL-CIR: Noise-aware Contrastive Learning For Composed Image Retrieval

Abstract

Composed Image Retrieval (CIR) seeks to find a target image using a multi-modal query, which combines an image with modification text to pinpoint the target. While recent CIR methods have shown promise, they mainly focus on exploring relationships between the query pairs (image and text) through data augmentation or model design. These methods often assume perfect alignment between queries and target images, an idealized scenario rarely encountered in practice. In reality, pairs are often partially or completely mismatched due to issues like inaccurate modification texts, low-quality target images, and annotation errors. Ignoring these mismatches leads to numerous False Positive Pair (FFPs) denoted as noise pairs in the dataset, causing the model to overfit and ultimately reducing its performance. To address this problem, we propose the Noise-aware Contrastive Learning for CIR (NCL-CIR), comprising two key components: the Weight Compensation Block (WCB) and the Noise-pair Filter Block

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keygao2025ncl

Related papers

• INTENT: Invariance And Discrimination-aware Noise Mitigation For Robust Composed Image Retrieval (2026)0.00
• Conesep: Cone-based Robust Noise-unlearning Compositional Network For Composed Image Retrieval (2026)0.00
• Improving Composed Image Retrieval Via Contrastive Learning With Scaling Positives And Negatives (2024)11.30
• Context-cir: Learning From Concepts In Text For Composed Image Retrieval (2025)4.67
• HINT: Composed Image Retrieval With Dual-path Compositional Contextualized Network (2026)0.78
• HABIT: Chrono-synergia Robust Progressive Learning Framework For Composed Image Retrieval (2026)2.35
• Compositional Image Retrieval Via Instruction-aware Contrastive Learning (2024)0.00
• Cala: Complementary Association Learning For Augmenting Composed Image Retrieval (2024)9.41