wy1iu / OPTLinks
Implementation for <Orthogonal Over-Parameterized Training> in CVPR'21.
☆19Updated 4 years ago
Alternatives and similar repositories for OPT
Users that are interested in OPT are comparing it to the libraries listed below
Sorting:
- A pytorch implementation of the ICCV2021 workshop paper SimDis: Simple Distillation Baselines for Improving Small Self-supervised Models☆14Updated 4 years ago
- This repository contains the code for our CVPR 2022 paper on "Non-isotropy Regularization for Proxy-based Deep Metric Learning".☆15Updated 2 years ago
- [CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jon…☆69Updated 2 years ago
- Repo for the paper "Extrapolating from a Single Image to a Thousand Classes using Distillation"☆36Updated last year
- Stochastic Optimization for Global Contrastive Learning without Large Mini-batches☆20Updated 2 years ago
- ☆14Updated 3 years ago
- Original code base for On Pretraining Data Diversity for Self-Supervised Learning☆13Updated 6 months ago
- This is a offical PyTorch/GPU implementation of SupMAE.☆78Updated 2 years ago
- Official Implementation for PlugIn Inversion☆16Updated 3 years ago
- Code for T-MARS data filtering☆35Updated last year
- [ICLR 2022] "As-ViT: Auto-scaling Vision Transformers without Training" by Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wa…☆76Updated 3 years ago
- This is a PyTorch implementation of the paperViP A Differentially Private Foundation Model for Computer Vision☆36Updated 2 years ago
- Official implementation of "Continual Learning by Modeling Intra-Class Variation" (MOCA). [TMLR 2023]☆16Updated 2 years ago
- This code provides a PyTorch implementation for OTTER (Optimal Transport distillation for Efficient zero-shot Recognition), as described …☆69Updated 3 years ago
- ☆38Updated last year
- Code for ICLR 2022 Paper, "Controlling Directions Orthogonal to a Classifier"☆35Updated 2 years ago
- ☆36Updated 2 years ago
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation