OOD Generalization

OOD: Out-of-Distribution

Out-of-distribution generalization asks whether models learn patterns that transfer beyond the data they were trained on, such as to new hospitals, locations, time periods, molecular structures, or task compositions. Common approaches include causal and invariant representation learning, domain-generalization methods such as GroupDRO, targeted data augmentation, and physics-informed or compositional models that encode structure. Other strategies adapt models at test time or use prompts, retrieval, uncertainty estimates, and validation proxies to select or adjust predictions under shift. Across vision, language, graphs, science, and robotics, strong in-distribution scores and larger pretraining sets often fail to ensure transfer, leaving realistic shift evaluation and the trade-off between adaptation and preserving useful prior knowledge as central challenges.

Latest papers

399 papers45 papers in the last four weeks, up 29% on the four weeks before. 0.3% of all new papers.

Enabling Validation for Robust Few-Shot Recognition
Jun 5, 2025Hanxin Wang, Tian Liu, Shu KongFew-Shot Learning Few-Shot Image Classification
University of Macau · Texas A&M University · Institute of Collaborative Innovation
GRIT: Out-of-Distribution Robustness from Finite and Noisy Invariant Pairs
May 30, 2025Ruqi Bai, Easton Currie, Yao Ji +3OOD Generalization Spurious Correlation Robustness
Purdue University · Georgia Institute of Technology
Disassociating performance from compositional feature learning
May 14, 2025George Dimitriadis, Spyridon SamothrakisRepresentation Learning OOD Generalization
Computer Science and Electronic Engineering Department of the University of Essex
BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
May 3, 2025Evan R. Antoniuk, Shehtab Zaman, Tal Ben-Nun +10OOD Generalization Molecular Property Prediction
Lawrence Livermore National Laboratory, Livermore, CA · Binghamton University, Binghamton, NY
Active Learning Enables Generation of Molecules that Advance the Known Pareto Front
Jan 3, 2025Evan R. Antoniuk, Peggy Li, Nathan Keilbart +3Molecular Optimization OOD Generalization
Large Pretraining Datasets Don't Guarantee Robustness after Fine-Tuning in Image Classification
Oct 28, 2024Jaedong Hwang, Brian Cheung, Zhang-Wei Hong +3Neural Network Robustness OOD Generalization
Massachusetts Institute of Technology
Generalization error of min-norm interpolators in transfer learning
Jun 20, 2024Yanke Song, Kenneth Gu, Sohom Bhattacharya +1OOD Generalization Cross-Domain Transfer Learning
Department of Statistics, Harvard University · Department of Statistics, Stanford University · Department of Statistics, University of Florida
Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts
May 29, 2024Lanting Fang, Yulian Yang, Yawei Zhang +3Causal Representation Learning Structural Causal Models
1Beijing Institue of Technology · Southeast University · Wuhan University
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization
Apr 25, 2022Minghui Chen, Cheng Wen, Feng Zheng +2Synthetic Data Augmentation Image Corruption Robustness
Department of Computer Science and Engineering, Southern University of Science and Technology · The University of Sydney · JD Explore Academy, JD.com Inc +1

Jun 5, 2025J/K move · Enter open · S save

Enabling Validation for Robust Few-Shot Recognition

Hanxin Wang, Tian Liu, Shu Kong

University of Macau · Texas A&M University · Institute of Collaborative Innovation

Few-Shot Learning Few-Shot Image Classification VLM Adaptation OOD Generalization

Open paper AskPDF arXiv

A key challenge in Few-Shot Recognition (FSR) is the scarcity of labeled task-specific data for training. Contemporary methods mitigate this challenge by exploiting pretrained Vision-Language Models (VLMs) for their learned transferable features. Some recent ones augment the scarce data by retrieving relevant yet out-of-distribution (OOD) examples from external data sources. However, they largely overlook an equally fundamental challenge: the absence of validation data for model selection and hyperparameter tuning. As a result, the adapted VLMs overfit the few-shot training data and generalize poorly to OOD test data. We show that retrieved data provide a natural source of validation, but their direct use creates a fundamental paradox. Since the retrieved samples are inherently OOD w.r.t the few-shot ID training data, adapting a VLM to the ID data constantly degrades its performance on the retrieved data. Consequently, conventional validation relying on the accuracy of retrieved data favors no adaptation and prevents improved generalization. To resolve this dilemma, we formulate validation as a multi-objective optimization (MOO) problem between performance gains on the few-shot ID data and the performance preservation on the retrieved data. We introduce a simple yet effective validation strategy by choosing an operating point on the Pareto front of the MOO problem. This strategy enables hyperparameter tuning, which had been unrealistically done by using test data, thereby mitigating overfitting and improving generalization. We integrate it into a stage-wise finetuning pipeline, termed Validation-Enabled Stage-wise Tuning (VEST). Extensive experiments on five established benchmarks show that VEST consistently outperforms existing approaches on both ID and OOD test data.