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

arXiv: https://arxiv.org/abs/2506.21538 · HTML: https://mlsanity.com/paper/2506.21538/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Visual Semantic Reasoning for Image-Text Matching](https://mlsanity.com/paper/1909.02701/) (2019)
- [Probabilistic Embeddings for Cross-Modal Retrieval](https://mlsanity.com/paper/2101.05068/) (2021)
- [Learning the Best Pooling Strategy for Visual Semantic Embedding](https://mlsanity.com/paper/2011.04305/) (2020)
- [Similarity Reasoning and Filtration for Image-Text Matching](https://mlsanity.com/paper/2101.01368/) (2021)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models](https://mlsanity.com/paper/1711.06420/) (2017)
- [FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing](https://mlsanity.com/paper/2305.17497/) (2023)
- [Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders](https://mlsanity.com/paper/2008.05231/) (2020)
- [Universal Weighting Metric Learning for Cross-Modal Matching](https://mlsanity.com/paper/2010.03403/) (2020)
- [Improving Cross-Modal Retrieval with Set of Diverse Embeddings](https://mlsanity.com/paper/2211.16761/) (2022)
- [Learning Dual Semantic Relations with Graph Attention for Image-Text Matching](https://mlsanity.com/paper/2010.11550/) (2020)
- [3SHNet: Boosting Image-Sentence Retrieval via Visual Semantic-Spatial Self-Highlighting](https://mlsanity.com/paper/2404.17273/) (2024)

## Built on by (most cited first, 1 of 1)

- [Brain-Inspired Multimodal Spiking Neural Network for Image-Text Retrieval](https://mlsanity.com/paper/2603.26787/) (2026)

## Abstract (arXiv)

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.