DQE-CIR: Distinctive Query Embeddings Through Learnable Attribute Weights And Target Relative Negative Sampling In Composed Image Retrieval

Abstract

Composed image retrieval (CIR) addresses the task of retrieving a target image by jointly interpreting a reference image and a modification text that specifies the intended change. Most existing methods are still built upon contrastive learning frameworks that treat the ground truth image as the only positive instance and all remaining images as negatives. This strategy inevitably introduces relevance suppression, where semantically related yet valid images are incorrectly pushed away, and semantic confusion, where different modification intents collapse into overlapping regions of the embedding space. As a result, the learned query representations often lack discriminativeness, particularly at fine-grained attribute modifications. To overcome these limitations, we propose distinctive query embeddings through learnable attribute weights and target relative negative sampling (DQE-CIR), a method designed to learn distinctive query embeddings by explicitly modeling target relative relevan

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypark2026dqe

Related papers

• Qure: Query-relevant Retrieval Through Hard Negative Sampling In Composed Image Retrieval (2025)2.35
• NCL-CIR: Noise-aware Contrastive Learning For Composed Image Retrieval (2025)2.26
• Improving Composed Image Retrieval Via Contrastive Learning With Scaling Positives And Negatives (2024)11.30
• A Sanity Check On Composed Image Retrieval (2026)0.00
• HINT: Composed Image Retrieval With Dual-path Compositional Contextualized Network (2026)0.78
• Scaling Prompt Instructed Zero Shot Composed Image Retrieval With Image-only Data (2025)0.00
• Context-cir: Learning From Concepts In Text For Composed Image Retrieval (2025)4.67
• Compositional Image Retrieval Via Instruction-aware Contrastive Learning (2024)0.00