TonyLianLong/CrossMAE
Official Implementation of the CrossMAE paper: Rethinking Patch Dependence for Masked Autoencoders
CrossMAE helps AI and machine learning researchers and practitioners efficiently pre-train image recognition models using large datasets like ImageNet. You input a large collection of images, and it outputs highly accurate, pre-trained models ready for fine-tuning on specific image classification tasks. This is for professionals building advanced computer vision systems.
133 stars. No commits in the last 6 months.
Use this if you need to pre-train high-performance image classification models more efficiently, even on a single GPU, and then fine-tune them for specialized image recognition applications.
Not ideal if you are not working with image recognition models or do not have the technical expertise to work with PyTorch implementations and model checkpoints.
Stars
133
Forks
7
Language
Python
License
—
Category
Last pushed
Apr 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TonyLianLong/CrossMAE"
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
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.