LeapLabTHU / EfficientTrainLinks
1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.
☆226Updated last year
Alternatives and similar repositories for EfficientTrain
Users that are interested in EfficientTrain are comparing it to the libraries listed below
Sorting:
- [BMVC 2024] PlainMamba: Improving Non-hierarchical Mamba in Visual Recognition☆87Updated 8 months ago
- This repository contains the pytorch code for our work IEEE ISBI 2024 paper "ConvLoRA and AdaBN Based Domain Adaptation via Self-Training…☆94Updated last year
- The official repo for [TPAMI'23] "Vision Transformer with Quadrangle Attention"☆227Updated 2 months ago
- Official PyTorch implementation of DiffuseMix : Label-Preserving Data Augmentation with Diffusion Models (CVPR'2024)☆129Updated 9 months ago
- [NeurIPS 2024 Spotlight ⭐️ & TPAMI 2025] Parameter-Inverted Image Pyramid Networks (PIIP)☆107Updated 4 months ago
- [CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"☆211Updated last year
- [ICLR2025] This repository is the official implementation of our Autoregressive Pretraining with Mamba in Vision☆88Updated 6 months ago
- Open source implementation of "Vision Transformers Need Registers"☆201Updated 2 months ago
- Official Code of Paper "Reversible Column Networks" "RevColv2"☆264Updated 2 years ago
- [NeurIPS'23] DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions☆62Updated last year
- ImageNet-1K data download, processing for using as a dataset☆126Updated 2 years ago
- ☆78Updated 9 months ago
- [CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".☆250Updated 2 years ago
- [NeurIPS 2024] official code release for our paper "Revisiting the Integration of Convolution and Attention for Vision Backbone".☆42Updated 11 months ago
- The official implementation for paper: Improving Knowledge Distillation via Regularizing Feature Norm and Direction☆24Updated 2 years ago
- a PyTorch re-implementation of ECCV 2022 paper based on Detectron2: k-means mask Transformer.☆79Updated 2 years ago
- ☆91Updated 2 years ago
- [CVPR 2024] Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities☆101Updated last year
- Official implementation for paper "Knowledge Diffusion for Distillation", NeurIPS 2023☆93Updated last year
- ☆116Updated last year
- Official implementation of SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference☆177Updated last year
- Project Page for "Multi-Task Dense Prediction via Mixture of Low-Rank Experts"☆86Updated 6 months ago
- Official Implementation for CVPR 2024 paper: CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor☆110Updated last year
- One summary of efficient segment anything models☆112Updated last year
- ☆51Updated 11 months ago
- [NeurIPS2024 Spotlight] The official implementation of MambaTree: Tree Topology is All You Need in State Space Model☆104Updated last year
- [CVPR24] Official Implementation of GEM (Grounding Everything Module)☆134Updated 8 months ago
- Official PyTorch implementation of Which Tokens to Use? Investigating Token Reduction in Vision Transformers presented at ICCV 2023 NIVT …☆35Updated 2 years ago
- Proteus (ICLR2025)☆54Updated 8 months ago
- [CVPR'23 & TPAMI'25] Hard Patches Mining for Masked Image Modeling & Bootstrap Masked Visual Modeling via Hard Patch Mining☆106Updated 8 months ago