sunyiyou / dynamic-k-activation
Code for ICCV 2019 paper "Adaptive Activation Thresholding: Dynamic Routing Type Behavior for Interpretability in Convolutional Neural Networks"
☆11Updated 4 years ago
Related projects: ⓘ
- ☆23Updated 5 years ago
- Experiments from "The Generalization-Stability Tradeoff in Neural Network Pruning": https://arxiv.org/abs/1906.03728.☆14Updated 3 years ago
- Code base for SRSGD.☆28Updated 4 years ago
- Implementation for <Regularizing Neural Networks via Minimizing Hyperspherical Energy> in CVPR'20.☆23Updated 4 years ago
- This github repository contains the official code for the paper, "Evolving Robust Neural Architectures to Defend from Adversarial Attacks…☆18Updated 9 months ago
- This project is the Torch implementation of our accepted CVPR 2019 paper, Iterative Normalization: Beyond Standardization towards Effic…☆24Updated 3 years ago
- Codebase for the paper "Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning"☆17Updated 3 years ago
- Successfully training approximations to full-rank matrices for efficiency in deep learning.☆16Updated 3 years ago
- Official Implementation of Convolutional Normalization: Improving Robustness and Training for Deep Neural Networks☆30Updated 2 years ago
- Codebase for the paper "A Gradient Flow Framework for Analyzing Network Pruning"☆21Updated 3 years ago
- [ICLR 2020] ”Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference“☆24Updated 2 years ago
- Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search☆17Updated last month
- ☆25Updated 4 years ago
- Code for BlockSwap (ICLR 2020).☆33Updated 3 years ago
- ICML 2019. Turn a pre-trained GAN model into a content-addressable model without retraining.☆22Updated last month
- Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks☆18Updated 4 years ago
- ☆46Updated last year
- structured sparsity regularization☆13Updated 4 years ago
- Paper and Code for "Curriculum Learning by Optimizing Learning Dynamics" (AISTATS 2021)☆18Updated 3 years ago
- Riemannian approach to batch normalization☆18Updated 6 years ago
- PyTorch and Torch implementation for our accepted CVPR 2020 paper (Oral): Controllable Orthogonalization in Training DNNs☆23Updated 3 years ago
- ☆13Updated 3 years ago
- ☆10Updated 4 years ago
- Percentile computation for pytorch☆19Updated 4 years ago
- ☆10Updated last month
- This is the pytorch re-implementation of the IterNorm☆37Updated 5 years ago
- [NeurIPS 2019] E2-Train: Training State-of-the-art CNNs with Over 80% Less Energy☆21Updated 4 years ago
- Meta-learning learning rates with higher☆12Updated 4 years ago
- Proximal Mean-field for Neural Network Quantization☆22Updated 4 years ago
- Revisiting Parameter Sharing for Automatic Neural Channel Number Search, NeurIPS 2020☆20Updated 3 years ago