nblt / F-SAMLinks
[CVPR 2024] Friendly Sharpness-Aware Minimization
☆35Updated last year
Alternatives and similar repositories for F-SAM
Users that are interested in F-SAM are comparing it to the libraries listed below
Sorting:
- ☆35Updated 3 years ago
- The official repo for CVPR2023 highlight paper "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization".☆84Updated 2 years ago
- Transformers trained on Tiny ImageNet☆60Updated 5 months ago
- Official implementation of AAAI 2023 paper "Parameter-efficient Model Adaptation for Vision Transformers"☆106Updated 2 years ago
- Code for 'Multi-level Logit Distillation' (CVPR2023)☆71Updated last year
- [BMVC 2022] Official repository for "How to Train Vision Transformer on Small-scale Datasets?"☆167Updated 2 years ago
- Official implementation of paper "Knowledge Distillation from A Stronger Teacher", NeurIPS 2022☆155Updated 3 years ago
- [NeurIPS'23] DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions☆62Updated last year
- A simple minimal implementation of Reversible Vision Transformers☆126Updated last year
- [ICLR 2024 Oral] Improving Convergence and Generalization Using Parameter Symmetries☆31Updated last year
- An official code release of the paper RGB no more: Minimally Decoded JPEG Vision Transformers☆57Updated 2 years ago
- Denoising Masked Autoencoders Help Robust Classification.☆67Updated 2 years ago
- Switch EMA: A Free Lunch for Better Flatness and Sharpness☆28Updated last year
- ☆191Updated last year
- Official Code for NeurIPS 2022 Paper: How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders☆68Updated 2 years ago
- ☆28Updated 2 years ago
- Official implementation for paper "Knowledge Diffusion for Distillation", NeurIPS 2023☆94Updated 2 years ago
- ☆58Updated 2 years ago
- PyTorch repository for ICLR 2022 paper (GSAM) which improves generalization (e.g. +3.8% top-1 accuracy on ImageNet with ViT-B/32)☆145Updated 3 years ago
- “SURE: SUrvey REcipes for building reliable and robust deep networks” (CVPR 2024) & (ECCV 2024 OOD-CV Challenge Winner)☆75Updated 5 months ago
- [ICLR 2022] "Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice" by Peihao Wang, Wen…☆83Updated 2 years ago
- [NeurIPS 2023] The PyTorch Implementation of Scheduled (Stable) Weight Decay.☆62Updated last year
- [Preprint] Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Prunin…☆41Updated 4 months ago
- [NeurIPS 2022] Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach -- Official Implementation☆47Updated 2 years ago
- Official PyTorch(MMCV) implementation of “Adversarial AutoMixup” (ICLR 2024 spotlight)☆71Updated last year
- [ICLR'23] Trainability Preserving Neural Pruning (PyTorch)☆34Updated 2 years ago
- [NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "EcoFormer: Energy-Saving Attention with Linear Complexity"☆73Updated 3 years ago
- [CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference☆30Updated last year
- 1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundatio…☆226Updated last year
- [NeurIPS'24] Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization☆38Updated last year