juntang-zhuang / GSAM
PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)
☆138Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for GSAM
- ☆58Updated last year
- Whitening for Self-Supervised Representation Learning | Official repository☆125Updated last year
- Train ImageNet *fast* in 500 lines of code with FFCV☆136Updated 6 months ago
- ☆32Updated last year
- Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)☆53Updated last year
- [CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jon…☆68Updated last year
- Official implementation of paper Gradient Matching for Domain Generalization☆116Updated 2 years ago
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆83Updated 2 years ago
- [NeurIPS'20] GradAug: A New Regularization Method for Deep Neural Networks☆93Updated 3 years ago
- This is the official GitHub for paper: On the Versatile Uses of Partial Distance Correlation in Deep Learning, in ECCV 2022☆172Updated last year
- Weight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)☆27Updated last year
- Official Pytorch's implementation of RotoGrad☆73Updated last year
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆72Updated last year
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from t…☆76Updated 2 years ago
- Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better perfo…☆89Updated 2 years ago
- [ICLR 2022] "Deep AutoAugment" by Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang☆61Updated 2 months ago
- Official PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)☆104Updated 2 years ago
- ☆103Updated last year
- Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.☆140Updated 3 years ago
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)☆101Updated 2 years ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆25Updated last year
- [NeurIPS'21] "AugMax: Adversarial Composition of Random Augmentations for Robust Training" by Haotao Wang, Chaowei Xiao, Jean Kossaifi, Z…☆124Updated 2 years ago
- Gradient Starvation: A Learning Proclivity in Neural Networks☆60Updated 3 years ago
- ☆105Updated last year
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆116Updated last year
- ☆38Updated 2 weeks ago
- TF/Keras code for DiffStride, a pooling layer with learnable strides.☆124Updated 2 years ago
- ☆58Updated 2 years ago
- Transformers trained on Tiny ImageNet☆47Updated 2 years ago
- Training vision models with full-batch gradient descent and regularization☆38Updated last year