Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval

• URL: http://arxiv.org/abs/2506.21538v1
• Date: Thu, 26 Jun 2025 17:55:34 GMT
• Title: Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval
• Authors: Hani Alomari, Anushka Sivakumar, Andrew Zhang, Chris Thomas,
• Abstract summary: Cross-modal image-text retrieval is challenging because of the diverse possible associations between content from different modalities.<n>Traditional methods learn a single-vector embedding to represent semantics of each sample.<n>Set-based approaches, which represent each sample with multiple embeddings, offer a promising alternative.
• Score: 0.5999777817331317
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-modal image-text retrieval is challenging because of the diverse possible associations between content from different modalities. Traditional methods learn a single-vector embedding to represent semantics of each sample, but struggle to capture nuanced and diverse relationships that can exist across modalities. Set-based approaches, which represent each sample with multiple embeddings, offer a promising alternative, as they can capture richer and more diverse relationships. In this paper, we show that, despite their promise, these set-based representations continue to face issues including sparse supervision and set collapse, which limits their effectiveness. To address these challenges, we propose Maximal Pair Assignment Similarity to optimize one-to-one matching between embedding sets which preserve semantic diversity within the set. We also introduce two loss functions to further enhance the representations: Global Discriminative Loss to enhance distinction among embeddings, and Intra-Set Divergence Loss to prevent collapse within each set. Our method achieves state-of-the-art performance on MS-COCO and Flickr30k without relying on external data.

Related papers

• Principled Multimodal Representation Learning [70.60542106731813]
  Multimodal representation learning seeks to create a unified representation space by integrating diverse data modalities.<n>Recent advances have investigated the simultaneous alignment of multiple modalities, yet several challenges remain.<n>We propose Principled Multimodal Representation Learning (PMRL), a novel framework that achieves simultaneous alignment of multiple modalities.
  arXiv  Detail & Related papers  (2025-07-23T09:12:25Z)
• CLAMP: Contrastive Learning with Adaptive Multi-loss and Progressive Fusion for Multimodal Aspect-Based Sentiment Analysis [0.6961946145048322]
  This paper introduces an end to end Contrastive Learning framework with Adaptive Multi-loss and Progressive Attention Fusion.<n>The framework is composed of three novel modules: Progressive Attention Fusion network, Multi-task Contrastive Learning, and Adaptive Multi-loss Aggregation.<n> evaluation on standard public benchmarks demonstrates that CLAMP consistently outperforms the vast majority of existing state of the art methods.
  arXiv  Detail & Related papers  (2025-07-21T11:49:57Z)
• BiXFormer: A Robust Framework for Maximizing Modality Effectiveness in Multi-Modal Semantic Segmentation [55.486872677160015]
  We reformulate multi-modal semantic segmentation as a mask-level classification task.<n>We propose BiXFormer, which integrates Unified Modality Matching (UMM) and Cross Modality Alignment (CMA)<n> Experiments on both synthetic and real-world multi-modal benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2025-06-04T08:04:58Z)
• Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation [12.308473939796945]
  Weakly supervised semantic segmentation (WSSS) with image-level labels aims to achieve dense tasks without laborious annotations. The performance of WSSS, especially the stages of generating Class Activation Maps (CAMs) and refining pseudo masks, widely suffers from ambiguity. We propose UniA, a unified single-staged WSSS framework, to tackle this issue from the perspective of uncertainty inference and affinity diversification.
  arXiv  Detail & Related papers  (2024-04-12T01:54:59Z)
• Cross-Modal Coordination Across a Diverse Set of Input Modalities [0.0]
  Cross-modal retrieval is the task of retrieving samples of a given modality by using queries of a different one. This paper proposes two approaches to the problem: the first is based on an extension of the CLIP contrastive objective to an arbitrary number of input modalities. The second departs from the contrastive formulation and tackles the coordination problem by regressing the cross-modal similarities towards a target.
  arXiv  Detail & Related papers  (2024-01-29T17:53:25Z)
• Preserving Modality Structure Improves Multi-Modal Learning [64.10085674834252]
  Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings without relying on human annotations. These methods often struggle to generalize well on out-of-domain data as they ignore the semantic structure present in modality-specific embeddings. We propose a novel Semantic-Structure-Preserving Consistency approach to improve generalizability by preserving the modality-specific relationships in the joint embedding space.
  arXiv  Detail & Related papers  (2023-08-24T20:46:48Z)
• M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition [80.21796574234287]
  M$3$Net is a matching-based framework for few-shot fine-grained (FS-FG) action recognition. It incorporates textitmulti-view encoding, textitmulti-view matching, and textitmulti-view fusion to facilitate embedding encoding, similarity matching, and decision making. Explainable visualizations and experimental results demonstrate the superiority of M$3$Net in capturing fine-grained action details.
  arXiv  Detail & Related papers  (2023-08-06T09:15:14Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• Improving Cross-Modal Retrieval with Set of Diverse Embeddings [19.365974066256026]
  Cross-modal retrieval across image and text modalities is a challenging task due to its inherent ambiguity. Set-based embedding has been studied as a solution to this problem. We present a novel set-based embedding method, which is distinct from previous work in two aspects.
  arXiv  Detail & Related papers  (2022-11-30T05:59:23Z)
• Hybrid Relation Guided Set Matching for Few-shot Action Recognition [51.3308583226322]
  We propose a novel Hybrid Relation guided Set Matching (HyRSM) approach that incorporates two key components. The purpose of the hybrid relation module is to learn task-specific embeddings by fully exploiting associated relations within and cross videos in an episode. We evaluate HyRSM on six challenging benchmarks, and the experimental results show its superiority over the state-of-the-art methods by a convincing margin.
  arXiv  Detail & Related papers  (2022-04-28T11:43:41Z)
• CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection [91.91911418421086]
  Co-Salient Object Detection (CoSOD) aims at discovering salient objects that repeatedly appear in a given query group containing two or more relevant images. One challenging issue is how to effectively capture co-saliency cues by modeling and exploiting inter-image relationships. We present an end-to-end collaborative aggregation-and-distribution network (CoADNet) to capture both salient and repetitive visual patterns from multiple images.
  arXiv  Detail & Related papers  (2020-11-10T04:28:11Z)
• COBRA: Contrastive Bi-Modal Representation Algorithm [43.33840912256077]
  We present a novel framework that aims to train two modalities in a joint fashion inspired by Contrastive Predictive Coding (CPC) and Noise Contrastive Estimation (NCE) paradigms. We empirically show that this framework reduces the modality gap significantly and generates a robust and task agnostic joint-embedding space. We outperform existing work on four diverse downstream tasks spanning across seven benchmark cross-modal datasets.
  arXiv  Detail & Related papers  (2020-05-07T18:20:12Z)

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.