# Reliable Cross-modal Alignment via Prototype Iterative Construction

arXiv: https://arxiv.org/abs/2510.11175 · HTML: https://mlsanity.com/paper/2510.11175/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning](https://mlsanity.com/paper/2104.03135/) (2021)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [Probabilistic Embeddings for Cross-Modal Retrieval](https://mlsanity.com/paper/2101.05068/) (2021)
- [Learning Deep Structure-Preserving Image-Text Embeddings](https://mlsanity.com/paper/1511.06078/) (2015)
- [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)
- [IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval](https://mlsanity.com/paper/2003.03772/) (2020)
- [Text to Image Generation with Semantic-Spatial Aware GAN](https://mlsanity.com/paper/2104.00567/) (2021)
- [Learning Dual Semantic Relations with Graph Attention for Image-Text Matching](https://mlsanity.com/paper/2010.11550/) (2020)
- [Image-Question-Answer Synergistic Network for Visual Dialog](https://mlsanity.com/paper/1902.09774/) (2019)

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

- [DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learning](https://mlsanity.com/paper/2602.00795/) (2026)

## Abstract (arXiv)

Cross-modal alignment is an important multi-modal task, aiming to bridge the semantic gap between different modalities. The most reliable fundamention for achieving this objective lies in the semantic consistency between matched pairs. Conventional methods implicitly assume embeddings contain solely semantic information, ignoring the impact of non-semantic information during alignment, which inevitably leads to information bias or even loss. These non-semantic information primarily manifest as stylistic variations in the data, which we formally define as style information. An intuitive approach is to separate style from semantics, aligning only the semantic information. However, most existing methods distinguish them based on feature columns, which cannot represent the complex coupling relationship between semantic and style information. In this paper, we propose PICO, a novel framework for suppressing style interference during embedding interaction. Specifically, we quantify the probability of each feature column representing semantic information, and regard it as the weight during the embedding interaction. To ensure the reliability of the semantic probability, we propose a prototype iterative construction method. The key operation of this method is a performance feedback-based weighting function, and we have theoretically proven that the function can assign higher weight to prototypes that bring higher performance improvements. Extensive experiments on various benchmarks and model backbones demonstrate the superiority of PICO, outperforming state-of-the-art methods by 5.2%-14.1%.