# DQE-CIR: Distinctive Query Embeddings through Learnable Attribute Weights and Target Relative Negative Sampling in Composed Image Retrieval

arXiv: https://arxiv.org/abs/2603.04037 · HTML: https://mlsanity.com/paper/2603.04037/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [Zero-Shot Composed Image Retrieval with Textual Inversion](https://mlsanity.com/paper/2303.15247/) (2023)
- [Vision-by-Language for Training-Free Compositional Image Retrieval](https://mlsanity.com/paper/2310.09291/) (2023)
- [Sentence-level Prompts Benefit Composed Image Retrieval](https://mlsanity.com/paper/2310.05473/) (2023)
- [Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features](https://mlsanity.com/paper/2308.11485/) (2023)
- [Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization](https://mlsanity.com/paper/2211.07394/) (2022)
- [Bi-directional Training for Composed Image Retrieval via Text Prompt Learning](https://mlsanity.com/paper/2303.16604/) (2023)
- [ParGo: Bridging Vision-Language with Partial and Global Views](https://mlsanity.com/paper/2408.12928/) (2024)
- [Target-Guided Composed Image Retrieval](https://mlsanity.com/paper/2309.01366/) (2023)
- [Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2403.16005/) (2024)
- [Cross-Modal Adapter for Vision-Language Retrieval](https://mlsanity.com/paper/2211.09623/) (2022)
- [CoLLM: A Large Language Model for Composed Image Retrieval](https://mlsanity.com/paper/2503.19910/) (2025)
- [Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives](https://mlsanity.com/paper/2404.11317/) (2024)
- [A Comprehensive Survey on Composed Image Retrieval](https://mlsanity.com/paper/2502.18495/) (2025)
- [HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding](https://mlsanity.com/paper/2503.08585/) (2025)
- [Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval](https://mlsanity.com/paper/2412.11087/) (2024)
- [Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks](https://mlsanity.com/paper/2410.09489/) (2024)
- [ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval](https://mlsanity.com/paper/2505.20764/) (2025)
- [ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval](https://mlsanity.com/paper/2410.18715/) (2024)
- [DisenQ: Disentangling Q-Former for Activity-Biometrics](https://mlsanity.com/paper/2507.07262/) (2025)
- [NCL-CIR: Noise-aware Contrastive Learning for Composed Image Retrieval](https://mlsanity.com/paper/2504.04339/) (2025)

## Abstract (arXiv)

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 relevance during training. DQE-CIR incorporates learnable attribute weighting to emphasize distinctive visual features conditioned on the modification text, enabling more precise feature alignment between language and vision. Furthermore, we introduce target relative negative sampling, which constructs a target relative similarity distribution and selects informative negatives from a mid-zone region that excludes both easy negatives and ambiguous false negatives. This strategy enables more reliable retrieval for fine-grained attribute changes by improving query discriminativeness and reducing confusion caused by semantically similar but irrelevant candidates.