AlexeyGB / batch-norm-helps-optimization
Reproduction of "How Does Batch Normalization Help Optimization?" paper
☆20Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for batch-norm-helps-optimization
- Code for ViTAS_Vision Transformer Architecture Search☆52Updated 3 years ago
- ☆29Updated 4 years ago
- PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"☆51Updated 3 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
- [NeurIPS 2020] "Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free" by Haotao Wang*, Tianlong C…☆43Updated 2 years ago
- released code for the paper: ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding☆30Updated 4 years ago
- Seach Losses of our paper 'Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search', accepted by ICLR 2021.☆56Updated 2 years ago
- [CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jon…☆68Updated last year
- ☆32Updated 3 years ago
- This is the official implementation of "DHP: Differentiable Meta Pruning via HyperNetworks".☆58Updated 2 years ago
- PyTorch implementation of Weighted Batch-Normalization layers☆37Updated 4 years ago
- An efficient implementation for ImageNet classification☆16Updated 4 years ago
- [ICLR 2022]: Fast AdvProp☆35Updated 2 years ago
- [TIP 2022] Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training. Plus, an image classification toolbox includes ResNet, …☆104Updated 2 years ago
- [CVPR 2020] Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning☆84Updated 2 years ago
- CVPR2021: Out-of-Distribution Detection Using Union of 1-Dimensional Subspaces☆22Updated 3 years ago
- Improving Contrastive Learning by Visualizing Feature Transformation, ICCV 2021 Oral☆89Updated 3 years ago
- ☆106Updated 2 years ago
- This repository provides code for "On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness".☆44Updated 2 years ago
- Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift (ICCV 2021)☆19Updated 2 years ago
- ReSSL: Relational Self-Supervised Learning with Weak Augmentation☆57Updated 2 years ago
- Automated Search for Resource-Efficient Branched Multi-Task Networks [BMVC 2020]☆15Updated last year
- This is the repo for the paper "Episodic Training for Domain Generalization" https://arxiv.org/abs/1902.00113☆56Updated last year
- ☆9Updated 3 years ago
- The Official Implementation of the ICCV-2021 Paper: Semantically Coherent Out-of-Distribution Detection.☆69Updated 2 years ago
- [NeurIPS'22] What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective☆36Updated last year
- This is the implementaion of paper "Task-Oriented Feature Distillation"☆42Updated 2 years ago
- This code accompanies the paper "Parameter-free Online Test-time Adaptation".☆66Updated 2 years ago
- Official repo for PAC-Bayes Information Bottleneck. ICLR 2022.☆46Updated 2 years ago
- ☆23Updated 3 years ago