Conesep: Cone-based Robust Noise-unlearning Compositional Network For Composed Image Retrieval

Abstract

The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on expensive and error-prone triplet annotations. This paper systematically investigates the Noisy Triplet Correspondence (NTC) problem introduced by annotations. We find that NTC noise, particularly ``hard noise'' (i.e., the reference and target images are highly similar but the modification text is incorrect), poses a unique challenge to existing Noise Correspondence Learning (NCL) methods because it breaks the traditional ``small loss hypothesis''. We identify and elucidate three key, yet overlooked, challenges in the NTC task, namely (C1) Modality Suppression, (C2) Negative Anchor Deficiency, and (C3) Unlearning Backlash. To address these challenges, we propose a Cone-based robuSt noisE-unlearning comPositional network (ConeSep). Specifically, we first propose Geometric Fidelity Quantization, theoretically establishing and practically est

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2026conesep

Related papers

• INTENT: Invariance And Discrimination-aware Noise Mitigation For Robust Composed Image Retrieval (2026)0.00
• NCL-CIR: Noise-aware Contrastive Learning For Composed Image Retrieval (2025)2.26
• HABIT: Chrono-synergia Robust Progressive Learning Framework For Composed Image Retrieval (2026)2.35
• Collaborative Group: Composed Image Retrieval Via Consensus Learning From Noisy Annotations (2023)0.00
• Air-know: Arbiter-calibrated Knowledge-internalizing Robust Network For Composed Image Retrieval (2026)0.00
• HINT: Composed Image Retrieval With Dual-path Compositional Contextualized Network (2026)0.78
• Context-cir: Learning From Concepts In Text For Composed Image Retrieval (2025)4.67
• Improving Composed Image Retrieval Via Contrastive Learning With Scaling Positives And Negatives (2024)11.30