enyac-group / Joslim
Official codebase for our paper "Joslim: Joint Widths and Weights Optimization for Slimmable Neural Networks"
☆12Updated 3 years ago
Alternatives and similar repositories for Joslim:
Users that are interested in Joslim are comparing it to the libraries listed below
- Codebase for the paper "Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning"☆17Updated 3 years ago
- ☆10Updated 4 years ago
- Codebase for the paper "A Gradient Flow Framework for Analyzing Network Pruning"☆21Updated 4 years ago
- ☆22Updated 5 years ago
- Pytorch implementation of our paper accepted by IEEE TNNLS, 2021 -- Network Pruning using Adaptive Exemplar Filters☆22Updated 3 years ago
- ☆9Updated 3 years ago
- Paper and Code for "Curriculum Learning by Optimizing Learning Dynamics" (AISTATS 2021)☆19Updated 3 years ago
- [ICLR 2022]: Fast AdvProp☆34Updated 2 years ago
- Repo for the paper "Extrapolating from a Single Image to a Thousand Classes using Distillation"☆36Updated 7 months ago
- A generic code base for neural network pruning, especially for pruning at initialization.☆30Updated 2 years ago
- This repository provides code for "On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness".☆45Updated 2 years ago
- TF-FD☆19Updated 2 years ago
- [ICML 2022] This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). We suggest to use an L…☆11Updated 2 years ago
- [ICLR 2020] ”Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference“☆24Updated 3 years ago
- Code for Active Mixup in 2020 CVPR☆22Updated 3 years ago
- Neuron Merging: Compensating for Pruned Neurons (NeurIPS 2020)☆43Updated 4 years ago
- Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection☆21Updated 4 years ago
- Learning from Limited and Imperfect Data (L2ID): Classification Challenges☆18Updated 4 years ago
- ☆29Updated 3 years ago
- ☆16Updated 2 years ago
- [ICLR 2021 Spotlight Oral] "Undistillable: Making A Nasty Teacher That CANNOT teach students", Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Che…☆81Updated 3 years ago
- ☆57Updated 3 years ago
- Code for the ICML 2021 and ICLR 2022 papers: Skew Orthogonal Convolutions, Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100☆18Updated 3 years ago
- Pytorch implementation of our paper accepted by IEEE TNNLS, 2022 — Carrying out CNN Channel Pruning in a White Box