# I0T: Embedding Standardization Method Towards Zero Modality Gap

arXiv: https://arxiv.org/abs/2412.14384 · HTML: https://mlsanity.com/paper/2412.14384/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Hopfield Networks is All You Need](https://mlsanity.com/paper/2008.02217/) (2020)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation](https://mlsanity.com/paper/2303.12112/) (2023)
- [SoftCLIP: Softer Cross-modal Alignment Makes CLIP Stronger](https://mlsanity.com/paper/2303.17561/) (2023)
- [Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning](https://mlsanity.com/paper/2303.05952/) (2023)
- [FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model](https://mlsanity.com/paper/2406.06004/) (2024)
- [Geodesic Multi-Modal Mixup for Robust Fine-Tuning](https://mlsanity.com/paper/2203.03897/) (2022)
- [It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap](https://mlsanity.com/paper/2405.18570/) (2024)
- [InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation](https://mlsanity.com/paper/2305.06002/) (2023)
- [Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP](https://mlsanity.com/paper/2406.17639/) (2024)
- [MCSE: Multimodal Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2204.10931/) (2022)
- [Alignment and stability of embeddings: measurement and inference improvement](https://mlsanity.com/paper/2101.07251/) (2021)

## Built on by (most cited first, 8 of 8)

- [Interpretable Debiasing of Vision-Language Models for Social Fairness](https://mlsanity.com/paper/2602.24014/) (2026)
- [TextME: Bridging Unseen Modalities Through Text Descriptions](https://mlsanity.com/paper/2602.03098/) (2026)
- [One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness](https://mlsanity.com/paper/2604.27674/) (2026)
- [How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions](https://mlsanity.com/paper/2502.14883/) (2025)
- [The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment](https://mlsanity.com/paper/2604.00279/) (2026)
- [COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings](https://mlsanity.com/paper/2605.29628/) (2026)
- [When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP](https://mlsanity.com/paper/2609.01103/) (2026)
- [Omni-Modal LLMs Know More Than They Say](https://mlsanity.com/paper/2610.16135/) (2026)

## Abstract (arXiv)

Contrastive Language-Image Pretraining (CLIP) enables zero-shot inference in downstream tasks such as image-text retrieval and classification. However, recent works extending CLIP suffer from the issue of modality gap, which arises when the image and text embeddings are projected to disparate manifolds, deviating from the intended objective of image-text contrastive learning. We discover that this phenomenon is linked to the modality-specific characteristic that each image/text encoder independently possesses and propose two methods to address the modality gap: (1) a post-hoc embedding standardization method, I0Tpost that reduces the modality gap approximately to zero and (2) a trainable method, I0Tasync, to alleviate the modality gap problem by adding two normalization layers for each encoder. Our I0T framework can significantly reduce the modality gap while preserving the original embedding representations of trained models with their locked parameters. In practice, I0Tpost can serve as an alternative explainable automatic evaluation metric of widely used CLIPScore (CLIP-S).