Official PyTorch implementation of A-ViT: Adaptive Tokens for Efficient Vision Transformer (CVPR 2022)
☆166Jul 14, 2022Updated 3 years ago
Alternatives and similar repositories for A-ViT
Users that are interested in A-ViT are comparing it to the libraries listed below
Sorting:
- [CVPR-22] This is the official implementation of the paper "Adavit: Adaptive vision transformers for efficient image recognition".☆56Aug 18, 2022Updated 3 years ago
- Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)☆104May 3, 2024Updated last year
- [NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification☆651Jul 11, 2023Updated 2 years ago
- Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations☆199Sep 3, 2023Updated 2 years ago
- Code for Learned Thresholds Token Merging and Pruning for Vision Transformers (LTMP). A technique to reduce the size of Vision Transforme…☆17Nov 24, 2024Updated last year
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,171Jun 17, 2024Updated last year
- ☆53Aug 28, 2024Updated last year
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆104Jul 14, 2023Updated 2 years ago
- ☆23Oct 24, 2022Updated 3 years ago
- (AAAI 2023 Oral) Pytorch implementation of "CF-ViT: A General Coarse-to-Fine Method for Vision Transformer"☆107Jul 4, 2023Updated 2 years ago
- ☆21Apr 24, 2022Updated 3 years ago
- SKT'22 AI Fellowship, 딥러닝 기반 흑백 이미지 컬러화 기술 개발☆13Jun 7, 2023Updated 2 years ago
- The codes for TCFormer in paper: Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer☆243Aug 3, 2024Updated last year
- Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.☆153Jan 14, 2022Updated 4 years ago
- Code Release for MeMViT Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition, CVPR 2022☆153Nov 30, 2022Updated 3 years ago
- ☆13Sep 24, 2023Updated 2 years ago
- 🥈12th place solution on G2Net Detecting Continuous Gravitational Waves🥈☆14Jan 4, 2023Updated 3 years ago
- Official Pytorch implementation of GGDR (ECCV 2022)☆102Aug 10, 2022Updated 3 years ago
- ☆28Nov 29, 2022Updated 3 years ago
- ☆214Dec 17, 2021Updated 4 years ago
- [ICCV 2021] Official PyTorch Code for "Online Knowledge Distillation for Efficient Pose Estimation"☆43Mar 8, 2024Updated last year
- Official code for "Top-Down Visual Attention from Analysis by Synthesis" (CVPR 2023 highlight)☆167Aug 20, 2023Updated 2 years ago
- [ECCV2022] Motion Sensitive Contrastive Learning for Self-supervised Video Representation☆17Aug 12, 2022Updated 3 years ago
- ☆18May 25, 2022Updated 3 years ago
- ☆43Aug 9, 2022Updated 3 years ago
- [ICML 2023] Official PyTorch implementation of Global Context Vision Transformers☆446Dec 22, 2023Updated 2 years ago
- 🎖️ 5th place solution in the Google American Sign Language Fingerspelling Recognition Competition🎖️☆16Sep 19, 2023Updated 2 years ago
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆74Jul 13, 2022Updated 3 years ago
- Official Pytorch Implementation of Self-emerging Token Labeling☆35Mar 27, 2024Updated last year
- [AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"☆97Jun 19, 2022Updated 3 years ago
- Pytorch implementation of Mix-Shifting-MLP (MS-MLP)☆16Feb 16, 2022Updated 4 years ago
- ☆31Mar 14, 2022Updated 3 years ago
- Official DeiT repository☆4,325Mar 15, 2024Updated last year
- [ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention☆906Jul 22, 2025Updated 7 months ago
- [ICLR 2022] RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning☆63Sep 10, 2022Updated 3 years ago
- [CVPR'23] AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders☆84Feb 2, 2024Updated 2 years ago
- EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]☆1,109Aug 13, 2023Updated 2 years ago
- This repo is the official megengine implementation of the ECCV2022 paper: Efficient One Pass Self-distillation with Zipf's Label Smoothin…☆28Oct 19, 2022Updated 3 years ago
- [ICCV 2023 & AAAI 2023] Binary Adapters & FacT, [Tech report] Convpass☆198Aug 1, 2023Updated 2 years ago