[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.
☆103Jul 14, 2023Updated 3 years ago
Alternatives and similar repositories for DiffRate
Users that are interested in DiffRate are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of "SViT: Revisiting Token Pruning for Object Detection and Instance Segmentation"☆37Dec 5, 2023Updated 2 years ago
- [ICLR 2022] "Unified Vision Transformer Compression" by Shixing Yu*, Tianlong Chen*, Jiayi Shen, Huan Yuan, Jianchao Tan, Sen Yang, Ji Li…☆54Dec 1, 2023Updated 2 years ago
- ☆48Aug 7, 2023Updated 3 years ago
- Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations☆202Jun 30, 2026Updated 4 months ago
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆73Jul 13, 2022Updated 4 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,205Jun 17, 2024Updated 2 years ago
- ☆15Feb 28, 2023Updated 3 years ago
- ALGM applied to Segmenter☆34May 27, 2024Updated 2 years ago
- This is an official implementation for "Making Vision Transformers Efficient from A Token Sparsification View".☆34Feb 17, 2025Updated last year
- Github repository for the paper Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers.☆33Feb 25, 2026Updated 8 months ago
- [ICML 2024] CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers☆34Dec 30, 2024Updated last year
- Official implementation of CVPR 2024 paper "Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers".☆40Jul 30, 2025Updated last year
- Pytorch implementation of our paper accepted by TPAMI 2023 — Lottery Jackpots Exist in Pre-trained Models☆35Jun 19, 2023Updated 3 years ago
- [CVPR2023] Practical Network Acceleration with Tiny Sets☆13Jul 28, 2023Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆35Aug 10, 2023Updated 3 years ago
- ☆53Aug 28, 2024Updated 2 years ago
- Official PyTorch implementation of A-ViT: Adaptive Tokens for Efficient Vision Transformer (CVPR 2022)☆168Jul 14, 2022Updated 4 years ago
- Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)☆105May 3, 2024Updated 2 years ago
- super-resolution; post-training quantization; model compression☆14Nov 10, 2023Updated 3 years ago
- [NIPS2023]Implementation of Foundation Model is Efficient Multimodal Multitask Model Selector☆37Mar 7, 2024Updated 2 years ago
- Pytorch implementation of our paper accepted by IEEE TNNLS, 2022 — Carrying out CNN Channel Pruning in a White Box☆18Feb 15, 2022Updated 4 years ago
- Official Repository for "HydraViT: Stacking Heads for a Scalable ViT" (NeurIPS'24)☆14May 19, 2025Updated last year
- Champion Solutions repository for Perception Test challenges in ICCV2023 workshop.☆14Oct 18, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [TPAMI 2024] This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.☆115Dec 30, 2023Updated 2 years ago
- [CVPR-22] This is the official implementation of the paper "Adavit: Adaptive vision transformers for efficient image recognition".☆56Aug 18, 2022Updated 4 years ago
- Official code for Cumulative Spatial Knowledge Distillation for Vision Transformers (ICCV-2023) https://openaccess.thecvf.com/content/ICC…☆15Nov 5, 2023Updated 3 years ago
- [NeurIPS 2020] "FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training" by Yonggan Fu, Ha…☆10Feb 13, 2022Updated 4 years ago
- [ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers☆103Dec 30, 2024Updated last year
- This repository contains papers for a comprehensive survey on accelerated generation techniques in Large Language Models (LLMs).☆11May 24, 2024Updated 2 years ago
- Code for ICCV23 paper "Automatic network pruning via Hilbert Schmidt independence criterion lasso under information bottleneck principle"☆19Aug 8, 2023Updated 3 years ago
- Code for COLING 2022 long paper: MetaPrompting: Learning to Learn Better Prompts☆23Jan 8, 2023Updated 3 years ago
- A user-friendly evaluation tool that encompasses all necessary components for boundary detection on PASCAL-Context and NYUD-v2 datasets.☆15Oct 31, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models☆176Mar 8, 2026Updated 8 months ago
- The codebase for paper "PPT: Token Pruning and Pooling for Efficient Vision Transformer"☆29Nov 17, 2024Updated 2 years ago
- Structured Pruning Adapters in PyTorch☆20Aug 30, 2023Updated 3 years ago
- [KDD'22] Learned Token Pruning for Transformers☆98Feb 27, 2023Updated 3 years ago
- PiX: Dynamic Channel Sampling for ConvNets (CVPR 2024)☆13Jun 14, 2024Updated 2 years ago
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆54Dec 30, 2024Updated last year
- ☆13Sep 24, 2023Updated 3 years ago
Are these results useful?