dzy3 / KCD
Pytorch implementation of our paper accepted by ECCV2022 -- Knowledge Condensation Distillation https://arxiv.org/abs/2207.05409
☆30Updated last year
Related projects: ⓘ
- ☆52Updated last year
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆69Updated 2 years ago
- ☆60Updated 2 years ago
- [ICCV 2021] Official implementation of "Scalable Vision Transformers with Hierarchical Pooling"☆30Updated 2 years ago
- Official PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"☆62Updated 2 years ago
- Official implementation of the paper "Function-Consistent Feature Distillation" (ICLR 2023)☆25Updated last year
- [ICLR2024] Exploring Target Representations for Masked Autoencoders☆52Updated 8 months ago
- [ECCV 2022] AMixer: Adaptive Weight Mixing for Self-attention Free Vision Transformers☆27Updated last year
- Official PyTorch implementation of Data-free Knowledge Distillation for Object Detection, WACV 2021.☆61Updated 2 years ago
- The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration☆86Updated 2 years ago
- Official Pytorch implementation of Super Vision Transformer (IJCV)☆42Updated last year
- Official implementation for paper "DyRep: Bootstrapping Training with Dynamic Re-parameterization", CVPR 2022☆42Updated 2 years ago
- ☆21Updated 2 years ago
- Official implementation of paper "Masked Distillation with Receptive Tokens", ICLR 2023.☆63Updated last year
- ☆22Updated last year
- This repo is the official megengine implementation of the ECCV2022 paper: Efficient One Pass Self-distillation with Zipf's Label Smoothin…☆25Updated last year
- Code and models for the paper Glance-and-Gaze Vision Transformer☆28Updated 3 years ago
- ☆23Updated 2 years ago
- Code for You Only Cut Once: Boosting Data Augmentation with a Single Cut, ICML 2022.☆103Updated last year
- [AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"☆90Updated 2 years ago
- Unified Architecture Search with Convolution, Transformer, and MLP (ECCV 2022)☆52Updated last year
- [ICCV 23]This is a Pytorch implementation of our paper "SMMix: Self-Motivated Image Mixing for Vision Transformers"☆15Updated last year
- PyTorch code and checkpoints release for VanillaKD: https://arxiv.org/abs/2305.15781☆71Updated 9 months ago
- [CVPR 2023 Highlight] Masked Image Modeling with Local Multi-Scale Reconstruction☆41Updated last year
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆85Updated last year
- ☆21Updated 2 years ago
- Official implementation of the paper "Masked Autoencoders are Efficient Class Incremental Learners"☆36Updated 3 months ago
- Code for Paper "Self-Distillation from the Last Mini-Batch for Consistency Regularization"☆41Updated last year
- Official implementation for "SimA: Simple Softmax-free Attention for Vision Transformers"☆34Updated 5 months ago
- The official project website of "NORM: Knowledge Distillation via N-to-One Representation Matching" (The paper of NORM is published in IC…