CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval

• URL: http://arxiv.org/abs/2601.03728v1
• Date: Wed, 07 Jan 2026 09:21:38 GMT
• Title: CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval
• Authors: Zhipeng Qian, Zihan Liang, Yufei Ma, Ben Chen, Huangyu Dai, Yiwei Ma, Jiayi Ji, Chenyi Lei, Han Li, Xiaoshuai Sun,
• Abstract summary: Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text.<n>We propose CSMCIR, a unified representation framework that achieves efficient query-target alignment through three synergistic components.
• Score: 54.15776146365823
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text, offering substantial advantages over single-modality retrieval systems. However, existing CIR methods suffer from representation space fragmentation: queries and targets comprise heterogeneous modalities and are processed by distinct encoders, forcing models to bridge misaligned representation spaces only through post-hoc alignment, which fundamentally limits retrieval performance. This architectural asymmetry manifests as three distinct, well-separated clusters in the feature space, directly demonstrating how heterogeneous modalities create fundamentally misaligned representation spaces from initialization. In this work, we propose CSMCIR, a unified representation framework that achieves efficient query-target alignment through three synergistic components. First, we introduce a Multi-level Chain-of-Thought (MCoT) prompting strategy that guides Multimodal Large Language Models to generate discriminative, semantically compatible captions for target images, establishing modal symmetry. Building upon this, we design a symmetric dual-tower architecture where both query and target sides utilize the identical shared-parameter Q-Former for cross-modal encoding, ensuring consistent feature representations and further reducing the alignment gap. Finally, this architectural symmetry enables an entropy-based, temporally dynamic Memory Bank strategy that provides high-quality negative samples while maintaining consistency with the evolving model state. Extensive experiments on four benchmark datasets demonstrate that our CSMCIR achieves state-of-the-art performance with superior training efficiency. Comprehensive ablation studies further validate the effectiveness of each proposed component.

Related papers

• A Simple and Effective Framework for Symmetric Consistent Indexing in Large-Scale Dense Retrieval [11.72564658353791]
  Dense retrieval has become the industry standard in large-scale information retrieval systems due to its high efficiency and competitive accuracy.<n>The widely adopted dual-tower encoding architecture introduces inherent challenges, primarily representational space misalignment and retrieval index inconsistency.<n>This paper proposes a simple and effective framework named SCI comprising two synergistic modules.<n>We provide theoretical guarantees for our approach, with its effectiveness validated by results across public datasets and real-world e-commerce datasets.
  arXiv  Detail & Related papers  (2025-12-15T08:11:24Z)
• CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning [93.05917922306196]
  Composed Image Retrieval (CIR) aims to find a target image from a reference image and a modification text.<n>CIR-CoT is the first end-to-end retrieval-oriented MLLM designed to integrate explicit Chain-of-Thought (CoT) reasoning.
  arXiv  Detail & Related papers  (2025-10-09T09:41:45Z)
• SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability [9.90112908284836]
  We introduce (Sparse Autoencoders for Aligned Representation of Concepts) a new framework that learns a single, unified latent space shared across diverse architectures.<n>On Open Images, dramatically improves concept alignment, achieving a Jaccard similarity of 0.80, more than tripling the alignment compared to previous methods.
  arXiv  Detail & Related papers  (2025-07-07T22:29:00Z)
• Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID [82.12123628480371]
  Unsupervised person re-identification (USL-VI-ReID) seeks to match pedestrian images of the same individual across different modalities without human annotations for model learning.<n>Previous methods unify pseudo-labels of cross-modality images through label association algorithms and then design contrastive learning framework for global feature learning.<n>We propose a Semantic-Aligned Learning with Collaborative Refinement (SALCR) framework, which builds up objective for specific fine-grained patterns emphasized by each modality.
  arXiv  Detail & Related papers  (2025-04-27T13:58:12Z)
• SketchYourSeg: Mask-Free Subjective Image Segmentation via Freehand Sketches [116.1810651297801]
  SketchYourSeg establishes freehand sketches as a powerful query modality for subjective image segmentation.<n>Our evaluations demonstrate superior performance over existing approaches across diverse benchmarks.
  arXiv  Detail & Related papers  (2025-01-27T13:07:51Z)
• ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling [11.129453244307369]
  FG-SBIR aims to minimize the distance between sketches and corresponding images in the embedding space.<n>We propose an effective approach to narrow the gap between the two domains.<n>It mainly facilitates unified mutual information sharing both intra- and inter-samples.
  arXiv  Detail & Related papers  (2024-06-17T13:49:12Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)
• CM-MaskSD: Cross-Modality Masked Self-Distillation for Referring Image Segmentation [29.885991324519463]
  We propose a novel cross-modality masked self-distillation framework named CM-MaskSD. Our method inherits the transferred knowledge of image-text semantic alignment from CLIP model to realize fine-grained patch-word feature alignment. Our framework can considerably boost model performance in a nearly parameter-free manner.
  arXiv  Detail & Related papers  (2023-05-19T07:17:27Z)
• Deep Diversity-Enhanced Feature Representation of Hyperspectral Images [87.47202258194719]
  We rectify 3D convolution by modifying its topology to enhance the rank upper-bound. We also propose a novel diversity-aware regularization (DA-Reg) term that acts on the feature maps to maximize independence among elements. To demonstrate the superiority of the proposed Re$3$-ConvSet and DA-Reg, we apply them to various HS image processing and analysis tasks.
  arXiv  Detail & Related papers  (2023-01-15T16:19:18Z)
• Unifying Flow, Stereo and Depth Estimation [121.54066319299261]
  We present a unified formulation and model for three motion and 3D perception tasks. We formulate all three tasks as a unified dense correspondence matching problem. Our model naturally enables cross-task transfer since the model architecture and parameters are shared across tasks.
  arXiv  Detail & Related papers  (2022-11-10T18:59:54Z)
• Instance and Pair-Aware Dynamic Networks for Re-Identification [16.32740680438257]
  Re-identification (ReID) is to identify the same instance across different cameras. We propose a novel end-to-end trainable dynamic convolution framework named Instance and Pair-Aware Dynamic Networks. In some datasets our algorithm outperforms state-of-the-art methods and in others, our algorithm achieves a comparable performance.
  arXiv  Detail & Related papers  (2021-03-09T12:34:41Z)

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.