OpenGVLab / DiffRateLinks
[ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging techniques, while incorporating a differentiable compression rate.
☆99Updated 2 years ago
Alternatives and similar repositories for DiffRate
Users that are interested in DiffRate are comparing it to the libraries listed below
Sorting:
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆34Updated 2 years ago
- [CVPR-22] This is the official implementation of the paper "Adavit: Adaptive vision transformers for efficient image recognition".☆55Updated 3 years ago
- ☆47Updated 2 years ago
- Official implementation for paper "Knowledge Diffusion for Distillation", NeurIPS 2023☆90Updated last year
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆73Updated 3 years ago
- Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations☆191Updated last year
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆46Updated 7 months ago
- [NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".☆185Updated last year
- [CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".☆247Updated 2 years ago
- [ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.☆72Updated last year
- Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)☆103Updated last year
- Official PyTorch implementation of A-ViT: Adaptive Tokens for Efficient Vision Transformer (CVPR 2022)☆161Updated 3 years ago
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆90Updated 2 years ago
- (NeurIPS 2023 spotlight) Large-scale Dataset Distillation/Condensation, 50 IPC (Images Per Class) achieves the highest 60.8% on original …☆129Updated 9 months ago
- [NeurIPS 2022] “M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design”, Hanxue …☆127Updated 2 years ago
- [ICML 2024] CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers.☆34Updated 7 months ago
- [ECCV 2024] Isomorphic Pruning for Vision Models☆73Updated last year
- ImageNet-1K data download, processing for using as a dataset☆109Updated 2 years ago
- The codebase for paper "PPT: Token Pruning and Pooling for Efficient Vision Transformer"☆25Updated 9 months ago
- ☆91Updated 2 years ago
- [ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers.☆105Updated 7 months ago
- [IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition☆51Updated 5 months ago
- [CVPR'23] SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer☆73Updated last year
- ☆12Updated last year
- [CVPR 2023] This repository includes the official implementation our paper "Masked Autoencoders Enable Efficient Knowledge Distillers"☆107Updated 2 years ago
- [CVPR2024] Efficient Dataset Distillation via Minimax Diffusion☆95Updated last year
- ☆27Updated 2 years ago
- ☆113Updated last year
- Official implementation of AAAI 2023 paper "Parameter-efficient Model Adaptation for Vision Transformers"☆105Updated 2 years ago
- [CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference☆30Updated last year