conradry/pixpro-with-weights
Pixel Propagation for unsupervised visual representation learning
This project offers a pre-trained image recognition model that helps computer vision engineers develop robust models even with limited labeled data. It takes in large collections of unlabeled images and outputs a foundational image encoder, which can then be fine-tuned for specific tasks like object detection or image classification. It's designed for researchers or practitioners building vision systems who need high-quality visual representations.
No commits in the last 6 months.
Use this if you need a strong, pre-trained image backbone to build your own computer vision models, especially when you have a lot of unlabeled image data but not enough labeled data for traditional supervised learning.
Not ideal if you're looking for an out-of-the-box solution for a specific computer vision task without further model development or if you lack the technical expertise to integrate pre-trained models into your workflow.
Stars
11
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 16, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/conradry/pixpro-with-weights"
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.