Source Code for Our NeurIPS-2024 Paper "What Variables Affect Out-of-Distribution Generalization in Pretrained Models?"
-
Updated
Dec 30, 2024 - Python
Source Code for Our NeurIPS-2024 Paper "What Variables Affect Out-of-Distribution Generalization in Pretrained Models?"
Code for the Conditional Mutual Information-Debiasing (CMID) method.
[WACV 2024] Source code for "Consolidating separate degradations model via weights fusion and distillation".
[ECCV Workshops 2024] BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation
Official code for the paper: "When and How Does CLIP Enable Domain and Compositional Generalization?" (ICML 2025 Spotlight)
Evaluation of non-ROI masking to improve OOD generalization in chest x-ray disease classification
Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions? (ICCV Workshops 2023)
Mitigating Spurious Correlations for Self-supervised Recommendation
Code for "Environment Diversification with Multi-head Neural Network for Invariant Learning" (NeurIPS 2022)
Möbius Transform for Mitigating Perspective Distortions in Representation Learning (ECCV 2024)
Source Code for Our ICML-2025 Paper "Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning"
Code for the ICML 2021 paper "Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization" by Sang Michael Xie, Tengyu Ma, Percy Liang
[CVPR 2024] Source code for "Diffusion-Based Adaptation for Classification of Unknown Degraded Images".
[ICML 2025] OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
Official code for "Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms"
Causal Disentangled Recommendation Against Preference Shifts (TOIS), 2023
The value of out-of-distribution data (ICML 2023)
[CVPR 2024] Improving out-of-distribution generalization in graphs via hierarchical semantic environments
Masking Strategies for Background Bias Removal in Computer Vision Models (ICCVW OODCV 2023 paper)
Code for Mind the Label Shift of Augmentation-based Graph OOD generalization (LiSA) in CVPR 2023. LiSA is a model-agnostic Graph OOD framework.
Add a description, image, and links to the ood-generalization topic page so that developers can more easily learn about it.
To associate your repository with the ood-generalization topic, visit your repo's landing page and select "manage topics."