cheerss/CrossFormer
The official code for the paper: https://openreview.net/forum?id=_PHymLIxuI
This project provides advanced image recognition capabilities by processing visual inputs and identifying objects or segmenting different parts of an image. It takes image data and outputs classifications, object locations, or detailed segmentation masks. It's designed for computer vision engineers and researchers working on systems that need to accurately understand complex visual scenes.
401 stars. No commits in the last 6 months.
Use this if you need a high-performance vision transformer model for tasks like object detection, image classification, or instance/semantic segmentation, especially when dealing with objects of various sizes in an image.
Not ideal if your application primarily involves basic image classification without a strong need for detailed object localization or understanding multi-scale features, or if you require an extremely lightweight model for edge devices.
Stars
401
Forks
49
Language
Python
License
MIT
Category
Last pushed
Jan 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cheerss/CrossFormer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.