# Geodesic Multi-Modal Mixup for Robust Fine-Tuning

arXiv: https://arxiv.org/abs/2203.03897 · HTML: https://mlsanity.com/paper/2203.03897/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 70 of its 119 references that are in the map.
- First posted on arXiv 8 Mar 2022.

## Builds on (most cited first, 30 of 70)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [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)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)

## Built on by (most cited first, 29 of 29)

- [Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models](https://mlsanity.com/paper/2404.07983/) (2024)
- [Towards Calibrated Robust Fine-Tuning of Vision-Language Models](https://mlsanity.com/paper/2311.01723/) (2023)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning](https://mlsanity.com/paper/2503.19900/) (2025)
- [It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap](https://mlsanity.com/paper/2405.18570/) (2024)
- [Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning](https://mlsanity.com/paper/2412.07909/) (2024)
- [CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation](https://mlsanity.com/paper/2305.14635/) (2023)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Post-pre-training for Modality Alignment in Vision-Language Foundation Models](https://mlsanity.com/paper/2504.12717/) (2025)
- [Improving Medical Multi-modal Contrastive Learning with Expert Annotations](https://mlsanity.com/paper/2403.10153/) (2024)
- [Data-Efficient Multimodal Fusion on a Single GPU](https://mlsanity.com/paper/2312.10144/) (2023)
- [RankCLIP: Ranking-Consistent Language-Image Pretraining](https://mlsanity.com/paper/2404.09387/) (2024)
- [Generalizable Person Re-identification via Balancing Alignment and Uniformity](https://mlsanity.com/paper/2411.11471/) (2024)
- [I0T: Embedding Standardization Method Towards Zero Modality Gap](https://mlsanity.com/paper/2412.14384/) (2024)
- [Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence](https://mlsanity.com/paper/2502.17028/) (2025)
- [Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions](https://mlsanity.com/paper/2506.11111/) (2025)
- [Is the Modality Gap a Bug or a Feature? A Robustness Perspective](https://mlsanity.com/paper/2603.29080/) (2026)
- [Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap](https://mlsanity.com/paper/2402.04416/) (2024)
- [D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models](https://mlsanity.com/paper/2510.09473/) (2025)
- [Consistent and Invariant Generalization Learning for Short-video Misinformation Detection](https://mlsanity.com/paper/2507.04061/) (2025)
- [T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2510.23484/) (2025)
- [EPLKG: Efficient Prompt Learning with Knowledge Graph](https://mlsanity.com/paper/2304.10805/) (2023)
- [Compositional Semantics for Open Vocabulary Spatio-semantic Representations](https://mlsanity.com/paper/2310.04981/) (2023)
- [Vision Generalist Model: A Survey](https://mlsanity.com/paper/2506.09954/) (2025)
- [BrokenBind: Universal Modality Exploration beyond Dataset Boundaries](https://mlsanity.com/paper/2602.06451/) (2026)
- [The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment](https://mlsanity.com/paper/2604.00279/) (2026)
- [IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation](https://mlsanity.com/paper/2604.01361/) (2026)
- [On the modality gap and the contrastive loss in multi-modal representation learning](https://mlsanity.com/paper/2607.10698/) (2026)
- [AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization](https://mlsanity.com/paper/2607.13805/) (2026)

## Abstract (arXiv)

Pre-trained multi-modal models, such as CLIP, provide transferable embeddings and show promising results in diverse applications. However, the analysis of learned multi-modal embeddings is relatively unexplored, and the embedding transferability can be improved. In this work, we observe that CLIP holds separated embedding subspaces for two different modalities, and then we investigate it through the lens of uniformity-alignment to measure the quality of learned representation. Both theoretically and empirically, we show that CLIP retains poor uniformity and alignment even after fine-tuning. Such a lack of alignment and uniformity might restrict the transferability and robustness of embeddings. To this end, we devise a new fine-tuning method for robust representation equipping better alignment and uniformity. First, we propose a Geodesic Multi-Modal Mixup that mixes the embeddings of image and text to generate hard negative samples on the hypersphere. Then, we fine-tune the model on hard negatives as well as original negatives and positives with contrastive loss. Based on the theoretical analysis about hardness guarantee and limiting behavior, we justify the use of our method. Extensive experiments on retrieval, calibration, few- or zero-shot classification (under distribution shift), embedding arithmetic, and image captioning further show that our method provides transferable representations, enabling robust model adaptation on diverse tasks. Code: https://github.com/changdaeoh/multimodal-mixup