# SHED: Style-Homogenized Embedding Alignment for Domain Generalization

arXiv: https://arxiv.org/abs/2605.16973 · HTML: https://mlsanity.com/paper/2605.16973/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 46 references that are in the map.
- First posted on arXiv 16 May 2026.

## Builds on (most cited first, 30 of 33)

- [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)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [Combined Scaling for Zero-shot Transfer Learning](https://mlsanity.com/paper/2111.10050/) (2021)
- [Domain Generalization by Mutual-Information Regularization with Pre-trained Models](https://mlsanity.com/paper/2203.10789/) (2022)
- [CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2310.01403/) (2023)
- [CLIPood: Generalizing CLIP to Out-of-Distributions](https://mlsanity.com/paper/2302.00864/) (2023)
- [Exploiting Domain-Specific Features to Enhance Domain Generalization](https://mlsanity.com/paper/2110.09410/) (2021)
- [LPT: Long-tailed Prompt Tuning for Image Classification](https://mlsanity.com/paper/2210.01033/) (2022)
- [Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts](https://mlsanity.com/paper/2309.10019/) (2023)
- [Batch Normalization Embeddings for Deep Domain Generalization](https://mlsanity.com/paper/2011.12672/) (2020)
- [Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification](https://mlsanity.com/paper/2310.08255/) (2023)
- [WATT: Weight Average Test-Time Adaptation of CLIP](https://mlsanity.com/paper/2406.13875/) (2024)
- [Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning](https://mlsanity.com/paper/2405.11756/) (2024)
- [Vision-Language Models are Strong Noisy Label Detectors](https://mlsanity.com/paper/2409.19696/) (2024)
- [LADA: Scalable Label-Specific CLIP Adapter for Continual Learning](https://mlsanity.com/paper/2505.23271/) (2025)

## Abstract (arXiv)

Domain generalization aims to enhance model robustness against unseen domains with embedding distribution shifts. While large-scale vision-language models like CLIP exhibit strong generalization, their direct image-text embedding alignment suffers from inherent information asymmetry: images encode both class semantics and domain-specific styles, whereas text prompts primarily convey basic class cues. This asymmetry hinders generalization to novel domains in realistic scenarios. To address this, we propose Style-Homogenized Embedding alignment for Domain-generalization (SHED), a novel CLIP-based method that aligns style-homogenized embeddings instead of raw representations from encoders in CLIP. During training, SHED removes domain-specific style centroids from both image embeddings computed per source domains and text embeddings which are averaged across diverse prompt templates and stripped of a global centroid. For inference, considering the lack of target domain information, SHED projects diverse textual domain centroids into the visual space and aggregates predictions via membership weighting. Extensive experiments on five benchmarks show SHED achieves state-of-the-art performance, outperforming prior methods significantly (e.g., +4.0% on DomainNet vs. standard fine-tuning).