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

• URL: http://arxiv.org/abs/2603.04037v1
• Date: Wed, 04 Mar 2026 13:17:44 GMT
• Title: DQE-CIR: Distinctive Query Embeddings through Learnable Attribute Weights and Target Relative Negative Sampling in Composed Image Retrieval
• Authors: Geon Park, Ji-Hoon Park, Seong-Whan Lee,
• Abstract summary: 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.<n>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.<n>We propose distinctive query embeddings through learnable attribute weights and target relative negative sampling.
• Score: 53.482391830683014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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.

Related papers

• QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval [24.699637275626998]
  Composed Image Retrieval (CIR) retrieves relevant images based on a reference image and accompanying text describing desired modifications.<n>This limitation arises because most methods employing contrastive learning treat the target image as positive and all other images in the batch as negatives.<n>We propose Query-Relevant Retrieval through Hard Negative Sampling (QuRe), which optimize a reward model objective to reduce false negatives.
  arXiv  Detail & Related papers  (2025-07-16T17:06:33Z)
• IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis [46.502962768034166]
  Zero-shot Referring Image identifies the instance mask that best aligns with a referring expression without training and fine-tuning.<n>Previous CLIP-based models exhibit a notable reduction in their capacity to discern relative spatial relationships of objects.<n>IteRPrimE outperforms previous state-of-the-art zero-shot methods, particularly excelling in out-of-domain scenarios.
  arXiv  Detail & Related papers  (2025-03-02T15:19:37Z)
• DualFocus: Integrating Plausible Descriptions in Text-based Person Re-identification [6.381155145404096]
  We introduce DualFocus, a unified framework that integrates plausible descriptions to enhance the interpretative accuracy of vision-language models in Person Re-identification tasks. To achieve a balance between coarse and fine-grained alignment of visual and textual embeddings, we propose the Dynamic Tokenwise Similarity (DTS) loss. The comprehensive experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid, DualFocus demonstrates superior performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-13T04:21:00Z)
• Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training [84.95281245784348]
  Overemphasizing co-occurrence relationships can cause the overfitting issue of the model. We provide a causal inference framework to show that the correlative features caused by the target object and its co-occurring objects can be regarded as a mediator.
  arXiv  Detail & Related papers  (2024-04-09T13:13:24Z)
• LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations [4.680881326162484]
  Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection.<n>A common augmentation technique in contrastive learning is random cropping followed by resizing.<n>We introduce LeOCLR, a framework that employs a novel instance discrimination approach and an adapted loss function.
  arXiv  Detail & Related papers  (2024-03-11T15:33:32Z)
• Reflection Invariance Learning for Few-shot Semantic Segmentation [53.20466630330429]
  Few-shot semantic segmentation (FSS) aims to segment objects of unseen classes in query images with only a few annotated support images. This paper proposes a fresh few-shot segmentation framework to mine the reflection invariance in a multi-view matching manner. Experiments on both PASCAL-$5textiti$ and COCO-$20textiti$ datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-01T15:14:58Z)
• Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation [12.754320302262533]
  We introduce a new negative Pruning technology for Unpaired image-to-image Translation (PUT) by sparsifying and ranking the patches. The proposed algorithm is efficient, flexible and enables the model to learn essential information between corresponding patches stably.
  arXiv  Detail & Related papers  (2022-04-23T08:31:18Z)
• A Contrastive Objective for Learning Disentangled Representations [32.36217153362305]
  Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. We present a new approach, proposing a new domain-wise contrastive objective for ensuring invariant representations. In an extensive evaluation, our method convincingly outperforms the state-of-the-art in terms of representation invariance, representation informativeness, and training speed.
  arXiv  Detail & Related papers  (2022-03-21T18:56:36Z)
• A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning [111.05365744744437]
  Unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. In this work, we first prove that for contrastive learning, inaccurate label assignment heavily impairs its generalization for semantic instance discrimination. Inspired by this theory, we propose a novel self-labeling refinement approach for contrastive learning.
  arXiv  Detail & Related papers  (2021-06-28T14:24:52Z)
• Semi-supervised Semantic Segmentation with Directional Context-aware Consistency [66.49995436833667]
  We focus on the semi-supervised segmentation problem where only a small set of labeled data is provided with a much larger collection of totally unlabeled images. A preferred high-level representation should capture the contextual information while not losing self-awareness. We present the Directional Contrastive Loss (DC Loss) to accomplish the consistency in a pixel-to-pixel manner.
  arXiv  Detail & Related papers  (2021-06-27T03:42:40Z)
• Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning [116.91819311885166]
  We propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to textbfCross-samples and Multi-level representation. Our method, termed as CsMl, has the ability to integrate multi-level visual representations across samples in a robust way.
  arXiv  Detail & Related papers  (2020-12-04T17:26:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.