Accelerating T2t-ViT by 1.6-3.6x.
☆259Nov 25, 2021Updated 4 years ago
Alternatives and similar repositories for Dynamic-Vision-Transformer
Users that are interested in Dynamic-Vision-Transformer are comparing it to the libraries listed below
Sorting:
- ☆22Oct 27, 2021Updated 4 years ago
- Jittor implementation of Vision Transformer with Deformable Attention☆32Mar 1, 2022Updated 4 years ago
- [NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification☆652Jul 11, 2023Updated 2 years ago
- [CVPR 2022] Official repository of AdaFocusV2.☆91Dec 15, 2024Updated last year
- A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sac…☆185Aug 27, 2023Updated 2 years ago
- [CVPR 2021] CondenseNet V2: Sparse Feature Reactivation for Deep Networks☆86Aug 27, 2022Updated 3 years ago
- ☆110Sep 15, 2021Updated 4 years ago
- [IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition☆53Mar 20, 2025Updated last year
- Resolution adaptive network☆153Jul 17, 2022Updated 3 years ago
- Official implementation of Dynamic Perceiver☆43Nov 16, 2023Updated 2 years ago
- [ECCV 2022] Learning to Weight Samples for Dynamic Early-exiting Networks☆38Sep 28, 2023Updated 2 years ago
- ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet☆1,194Oct 27, 2023Updated 2 years ago
- Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better perfo…☆90Oct 12, 2022Updated 3 years ago
- [CVPR 2022] Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding☆153Jul 13, 2024Updated last year
- This is an official implementation for "ResT: An Efficient Transformer for Visual Recognition".☆292Sep 28, 2022Updated 3 years ago
- [NeurIPS 2022] Latency-aware Spatial-wise Dynamic Networks☆25Aug 21, 2023Updated 2 years ago
- Official implementation of the paper Visual Parser: Representing Part-whole Hierarchies with Transformers☆121Aug 12, 2021Updated 4 years ago
- ☆19Mar 5, 2025Updated last year
- ☆54Jan 2, 2025Updated last year
- MLP-Like Vision Permutator for Visual Recognition (PyTorch)☆192Mar 31, 2022Updated 3 years ago
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆92Mar 16, 2023Updated 3 years ago
- [NeurIPS 2023] Rank-DETR for High Quality Object Detection☆105Oct 19, 2023Updated 2 years ago
- [ECCV 2024] Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators☆47Sep 11, 2024Updated last year
- code base for vision transformers☆36Dec 4, 2021Updated 4 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
- Pytorch implementation of "All Tokens Matter: Token Labeling for Training Better Vision Transformers"☆433Sep 5, 2023Updated 2 years ago
- Two simple and effective designs of vision transformer, which is on par with the Swin transformer☆608Feb 14, 2023Updated 3 years ago
- Reducing spatial redundancy in video recognition. SOTA computational efficiency.☆127Dec 15, 2024Updated last year
- An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.☆593Apr 23, 2021Updated 4 years ago
- ☆249Mar 16, 2022Updated 4 years ago
- Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Atte…☆925Apr 17, 2024Updated last year
- Official implementation of PVT series☆1,888Oct 27, 2022Updated 3 years ago
- Official implementation of A Mixture of Surprises for Unsupervised Reinforcement Learning☆23Nov 16, 2022Updated 3 years ago
- ☆28Oct 6, 2022Updated 3 years ago
- [ECCV'20 Oral] MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution☆159Oct 4, 2022Updated 3 years ago
- (CVPR 2021, Oral) Dynamic Slimmable Network☆231Dec 31, 2021Updated 4 years ago
- VOLO: Vision Outlooker for Visual Recognition☆950Sep 18, 2022Updated 3 years ago
- MSDNet☆190Jan 7, 2022Updated 4 years ago
- ☆37Jan 18, 2023Updated 3 years ago