uzh-rpg / svit
Official implementation of "SViT: Revisiting Token Pruning for Object Detection and Instance Segmentation"
☆28Updated last year
Alternatives and similar repositories for svit:
Users that are interested in svit are comparing it to the libraries listed below
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆33Updated last year
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆92Updated last year
- Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)☆97Updated 8 months ago
- [CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference☆26Updated 10 months ago
- ☆26Updated 2 years ago
- This is an official implementation for "Making Vision Transformers Efficient from A Token Sparsification View".☆31Updated 7 months ago
- Offical Code for Paper "Exploring Inter-Channel Correlation for Diversity-preserved Knowledge Distillation"☆16Updated 3 years ago
- [CVPR'23] SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer☆62Updated 9 months ago
- [NeurIPS'23] DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions☆60Updated 9 months ago
- The official project website of "NORM: Knowledge Distillation via N-to-One Representation Matching" (The paper of NORM is published in IC…☆19Updated last year
- [CVPR-22] This is the official implementation of the paper "Adavit: Adaptive vision transformers for efficient image recognition".☆51Updated 2 years ago
- Official Pytorch implementation of Dynamic-Token-Pruning (ICCV2023)☆19Updated last year
- ☆32Updated last year
- Mosaic Representation Learning for Self-supervised Visual Pre-training (ICLR2023, Spotlight)☆15Updated last year
- ☆22Updated 2 years ago
- Official PyTorch implementation of Agglomerative Token Clustering presented at ECCV 2024☆13Updated 4 months ago
- [BMVC 2024] PlainMamba: Improving Non-hierarchical Mamba in Visual Recognition☆72Updated 5 months ago
- ☆42Updated last year
- The codebase for paper "PPT: Token Pruning and Pooling for Efficient Vision Transformer"☆20Updated 2 months ago
- Official code for "Opening up Open World Tracking" (CVPR 2022)☆55Updated last year
- This repository is the official implementation of our Autoregressive Pretraining with Mamba in Vision☆68Updated 7 months ago
- ☆32Updated 2 years ago
- [ICCV 2023] Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment☆43Updated last year
- Official implementation of CVPR 2024 paper "Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers".☆31Updated 9 months ago
- Code for our paper "Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers"☆35Updated last year
- [AAAI 2023 Oral] CoMAE: Single Model Hybrid Pre-training on Small-Scale RGB-D Datasets☆34Updated 5 months ago
- [ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.☆65Updated last year
- This is the official code for paper: Token Summarisation for Efficient Vision Transformers via Graph-based Token Propagation☆26Updated last year
- [2024 ECCV Workshop] Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion☆30Updated 4 months ago
- (NeurIPS 2024) Official repository of paper "Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models"☆24Updated 2 months ago