d3tk/REOrder
Does patch ordering affect context-limited vision transformers?
REOrder helps improve the accuracy of vision models that analyze images by intelligently reordering how different parts of an image are processed. It takes your image dataset and a trained vision transformer model, and outputs a more accurate version of that model. This is for machine learning engineers and researchers who are building and fine-tuning advanced computer vision systems.
No commits in the last 6 months.
Use this if you are working with vision transformers and want to boost their performance on specific image classification or analysis tasks by optimizing how image patches are sequenced.
Not ideal if you are looking for a plug-and-play solution for basic image processing or if you do not work with vision transformer architectures.
Stars
17
Forks
1
Language
Python
License
MIT
Category
Last pushed
Oct 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/d3tk/REOrder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BR-IDL/PaddleViT
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
pathak22/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
IBM/CrossViT
Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
NVlabs/GCVit
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
ViTAE-Transformer/ViTDet
Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object...