changsn / STViT-R
This is an official implementation for "Making Vision Transformers Efficient from A Token Sparsification View".
☆32Updated 7 months ago
Alternatives and similar repositories for STViT-R:
Users that are interested in STViT-R are comparing it to the libraries listed below
- Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)☆97Updated 9 months ago
- [NeurIPS'23] DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions☆61Updated 9 months ago
- ☆32Updated last year
- ☆85Updated last year
- ☆47Updated 2 years ago
- [ICCV'2023 Oral] Implicit Temporal Modeling with Learnable Alignment for Video Recognition☆33Updated last year
- Video Test-Time Adaptation for Action Recognition (CVPR 2023)☆39Updated 4 months ago
- AFNet(NeurIPS 2022)☆19Updated 2 years ago
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆33Updated last year
- ☆59Updated last year
- Official Implementation of AlignMixup - CVPR 2022☆71Updated 2 years ago
- Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations☆175Updated last year
- [CVPR2024] The code of "UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory"☆66Updated 4 months ago
- The official repository for ICLR2024 paper "FROSTER: Frozen CLIP is a Strong Teacher for Open-Vocabulary Action Recognition"☆69Updated last month
- [AAAI 2022] This is the official PyTorch implementation of "Less is More: Pay Less Attention in Vision Transformers"☆94Updated 2 years ago
- (AAAI 2023 Oral) Pytorch implementation of "CF-ViT: A General Coarse-to-Fine Method for Vision Transformer"☆103Updated last year
- [CVPR 2023 Highlight] Masked Image Modeling with Local Multi-Scale Reconstruction☆46Updated last year
- Official PyTorch implementation of the ECCV 2022 paper: Efficient Video Transformers with Spatial-Temporal Token Selection.☆46Updated 2 years ago
- LoMaR (Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction)☆62Updated 2 years ago
- SeqTR: A Simple yet Universal Network for Visual Grounding☆131Updated 3 months ago
- [CVPR 2023] Enlarge Instance-specific and Class-specific Information for Open-set Action Recognition☆27Updated last year
- ☆28Updated last year
- Codes for ECCV2022 paper - contrastive deep supervision☆68Updated 2 years ago
- A Siamese self-supervised pretraining approach for the Transformer architecture in DETR☆35Updated last year
- ☆73Updated last year
- Self-Supervised Video Representation Learning with Motion-Aware Masked Autoencoders☆23Updated 6 months ago
- ☆25Updated last year
- Multi-Scale Spatio-Temporal Attention based Video Instance Segmentation☆40Updated 2 years ago
- ☆37Updated 2 years ago
- OVSegmentor, CVPR23☆58Updated 9 months ago