blackfeather-wang / InfoPro-Pytorch
Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.
☆89Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for InfoPro-Pytorch
- [CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jon…☆68Updated last year
- ☆47Updated 4 years ago
- ☆29Updated 4 years ago
- Code for ViTAS_Vision Transformer Architecture Search☆52Updated 3 years ago
- [ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Che…☆81Updated 2 years ago
- Implementation of Effective Sparsification of Neural Networks with Global Sparsity Constraint☆28Updated 2 years ago
- [CVPR 2021] Contrastive Neural Architecture Search with Neural Architecture Comparators☆40Updated 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
- ☆21Updated 5 years ago
- PyTorch implementation of Weighted Batch-Normalization layers☆37Updated 4 years ago
- [NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang…☆90Updated 11 months ago
- Code for our paper "Informative Dropout for Robust Representation Learning: A Shape-bias Perspective" (ICML 2020)☆125Updated last year
- Compressing Representations for Self-Supervised Learning☆78Updated 3 years ago
- An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation St…☆47Updated 3 years ago
- Code and pretrained models for paper: Data-Free Adversarial Distillation☆95Updated last year
- (ICCV 2021) BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search☆137Updated 2 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
- PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"☆51Updated 3 years ago
- Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning.☆149Updated 2 years ago
- [ICLR 2022]: Fast AdvProp☆35Updated 2 years ago
- Source code accompanying our CVPR 2019 paper: "NetTailor: Tuning the architecture, not just the weights."☆52Updated 3 years ago
- ☆56Updated 3 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
- Code for our ICLR'2021 paper "DrNAS: Dirichlet Neural Architecture Search"☆43Updated 3 years ago
- Improving Contrastive Learning by Visualizing Feature Transformation, ICCV 2021 Oral☆89Updated 3 years ago
- Official PyTorch implementation of "Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity" (ICLR'21 Oral)☆104Updated 2 years ago
- code for NASViT☆66Updated 2 years ago
- This is the code of CVPR'20 paper "Distilling Cross-Task Knowledge via Relationship Matching".☆48Updated 3 years ago
- Code for our ICML'2020 paper "Stabilizing Differentiable Architecture Search via Perturbation-based Regularization"☆76Updated 3 years ago
- Source Code for ICML 2019 Paper "Shallow-Deep Networks: Understanding and Mitigating Network Overthinking"☆35Updated 11 months ago