# CLIPood: Generalizing CLIP to Out-of-Distributions

arXiv: https://arxiv.org/abs/2302.00864 · HTML: https://mlsanity.com/paper/2302.00864/

## Key facts

- Cited by 96 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 71 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 30 of 53)

- [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)
- [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)
- [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)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [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)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [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)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)

## Built on by (most cited first, 30 of 96)

- [Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2407.08268/) (2024)
- [ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time](https://mlsanity.com/paper/2410.06625/) (2024)
- [Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification](https://mlsanity.com/paper/2310.08255/) (2023)
- [Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey](https://mlsanity.com/paper/2407.21794/) (2024)
- [Towards Calibrated Robust Fine-Tuning of Vision-Language Models](https://mlsanity.com/paper/2311.01723/) (2023)
- [DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning](https://mlsanity.com/paper/2403.08506/) (2024)
- [GalLoP: Learning Global and Local Prompts for Vision-Language Models](https://mlsanity.com/paper/2407.01400/) (2024)
- [A Simple Recipe for Language-guided Domain Generalized Segmentation](https://mlsanity.com/paper/2311.17922/) (2023)
- [PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration](https://mlsanity.com/paper/2407.00203/) (2024)
- [DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification](https://mlsanity.com/paper/2305.15957/) (2023)
- [Adapting to Distribution Shift by Visual Domain Prompt Generation](https://mlsanity.com/paper/2405.02797/) (2024)
- [A Practitioner's Guide to Continual Multimodal Pretraining](https://mlsanity.com/paper/2408.14471/) (2024)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data](https://mlsanity.com/paper/2310.05010/) (2023)
- [Robust Domain Generalization for Multi-modal Object Recognition](https://mlsanity.com/paper/2408.05831/) (2024)
- [Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization](https://mlsanity.com/paper/2401.15914/) (2024)
- [Vision-Language Models are Strong Noisy Label Detectors](https://mlsanity.com/paper/2409.19696/) (2024)
- [PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization](https://mlsanity.com/paper/2404.09011/) (2024)
- [Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection](https://mlsanity.com/paper/2409.04796/) (2024)
- [CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey](https://mlsanity.com/paper/2504.14280/) (2025)
- [Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization](https://mlsanity.com/paper/2407.15085/) (2024)
- [LanDA: Language-Guided Multi-Source Domain Adaptation](https://mlsanity.com/paper/2401.14148/) (2024)
- [CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring](https://mlsanity.com/paper/2405.14737/) (2024)
- [QT-DoG: Quantization-aware Training for Domain Generalization](https://mlsanity.com/paper/2410.06020/) (2024)
- [Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts](https://mlsanity.com/paper/2405.18861/) (2024)
- [SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning](https://mlsanity.com/paper/2407.03036/) (2024)
- [Diverse Target and Contribution Scheduling for Domain Generalization](https://mlsanity.com/paper/2309.16460/) (2023)
- [FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detector](https://mlsanity.com/paper/2412.05293/) (2024)
- [Is Large-Scale Pretraining the Secret to Good Domain Generalization?](https://mlsanity.com/paper/2412.02856/) (2024)
- [Improving CLIP Robustness with Knowledge Distillation and Self-Training](https://mlsanity.com/paper/2309.10361/) (2023)

## Abstract (arXiv)

Out-of-distribution (OOD) generalization, where the model needs to handle distribution shifts from training, is a major challenge of machine learning. Contrastive language-image pre-training (CLIP) models have shown impressive zero-shot ability, but the further adaptation of CLIP on downstream tasks undesirably degrades OOD performances. This paper aims at generalizing CLIP to out-of-distribution test data on downstream tasks. We propose CLIPood, a fine-tuning method that can adapt CLIP models to OOD situations where both domain shifts and open classes may occur on the unseen test data. To exploit the semantic relations between classes from the text modality, CLIPood introduces a new training objective, margin metric softmax (MMS), with class adaptive margins for fine-tuning. To incorporate both pre-trained zero-shot model and fine-tuned task-adaptive model, CLIPood leverages a new optimization strategy, Beta moving average (BMA), to maintain a temporal ensemble weighted by Beta distribution. Experiments on diverse datasets with different OOD scenarios show that CLIPood consistently outperforms existing generalization techniques.