OpenGVLab / DiffRate
[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.
☆89Updated last year
Related projects ⓘ
Alternatives and complementary repositories for DiffRate
- ☆42Updated last year
- [CVPR-22] This is the official implementation of the paper "Adavit: Adaptive vision transformers for efficient image recognition".☆49Updated 2 years ago
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆31Updated last year
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆91Updated last year
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆69Updated 2 years ago
- [ICML 2024] CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers.☆26Updated last year
- Official PyTorch implementation of A-ViT: Adaptive Tokens for Efficient Vision Transformer (CVPR 2022)☆149Updated 2 years ago
- [ICCV 2023 oral] This is the official repository for our paper: ''Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning''.☆64Updated last year
- [CVPR'23] SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer☆61Updated 6 months ago
- Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)☆94Updated 6 months ago
- [IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition☆41Updated 6 months ago
- ☆24Updated last year
- Official implementation for paper "Knowledge Diffusion for Distillation", NeurIPS 2023☆76Updated 9 months ago
- Official implementation of Dynamic Perceiver☆41Updated last year
- [ICLR2024] Exploring Target Representations for Masked Autoencoders☆51Updated 10 months ago
- [CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference☆25Updated 8 months ago
- [CVPR 2023] This repository includes the official implementation our paper "Masked Autoencoders Enable Efficient Knowledge Distillers"☆99Updated last year
- [NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".☆173Updated last year
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆36Updated last month
- [TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.☆107Updated 10 months ago
- Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations☆171Updated last year
- ☆108Updated 5 months ago
- Implementation of HAT https://arxiv.org/pdf/2204.00993☆47Updated 7 months ago
- ☆9Updated last year
- [CVPR2024] Efficient Dataset Distillation via Minimax Diffusion☆80Updated 7 months ago
- (NeurIPS 2023 spotlight) Large-scale Dataset Distillation/Condensation, 50 IPC (Images Per Class) achieves the highest 60.8% on original …☆119Updated this week
- [NeurIPS 2022] “M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design”, Hanxue …☆97Updated last year
- ☆100Updated 8 months ago
- ☆75Updated last year
- [BMVC 2024] PlainMamba: Improving Non-hierarchical Mamba in Visual Recognition☆70Updated 3 months ago