NVlabs / A-ViT
Official PyTorch implementation of A-ViT: Adaptive Tokens for Efficient Vision Transformer (CVPR 2022)
☆149Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for A-ViT
- Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations☆171Updated last year
- Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)☆94Updated 6 months ago
- [CVPR-22] This is the official implementation of the paper "Adavit: Adaptive vision transformers for efficient image recognition".☆49Updated 2 years ago
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆89Updated last year
- PyTorch implementation of the paper "MILAN: Masked Image Pretraining on Language Assisted Representation" https://arxiv.org/pdf/2208.0604…☆79Updated 2 years ago
- [ICLR2024] Exploring Target Representations for Masked Autoencoders☆51Updated 10 months ago
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆69Updated 2 years ago
- [CVPR 2023] This repository includes the official implementation our paper "Masked Autoencoders Enable Efficient Knowledge Distillers"☆99Updated last year
- Official Codes for "Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality"☆238Updated last year
- [AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"☆92Updated 2 years ago
- [ECCV 2022] EdgeViT: Competing Light-weight CNNs on Mobile Devices with Vision Transformers☆100Updated last year
- A PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-Supervised Learning Framework".☆83Updated 9 months ago
- Official repository for "Intriguing Properties of Vision Transformers" (NeurIPS 2021--Spotlight)☆176Updated 2 years ago
- [NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".☆173Updated last year
- [TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.☆107Updated 10 months ago
- TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers (ECCV 2022)☆93Updated 2 years ago
- ECCV2022,Bootstrapped Masked Autoencoders for Vision BERT Pretraining☆98Updated 2 years ago
- FastMIM, official pytorch implementation of our paper "FastMIM: Expediting Masked Image Modeling Pre-training for Vision"(https://arxiv.o…☆39Updated last year
- Official PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"☆62Updated 2 years ago
- [TPAMI] Searching prompt modules for parameter-efficient transfer learning.☆222Updated 11 months ago
- Accelerating T2t-ViT by 1.6-3.6x.☆246Updated 2 years ago
- LoMaR (Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction)☆61Updated 2 years ago
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆31Updated last year
- ☆244Updated last year
- This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".☆118Updated 2 years ago
- [NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification☆572Updated last year
- ☆100Updated 8 months ago
- [ICCV 2023 & AAAI 2023] Binary Adapters & FacT, [Tech report] Convpass☆171Updated last year
- The implementation of our paper: Towards Robust Vision Transformer (CVPR2022)☆138Updated 2 years ago
- ☆42Updated last year