hynnsk/HP
This is the official pytorch implementation of "Leveraging Hidden Positives for Unsupervised Semantic Segmentation" (CVPR 2023).
This project helps computer vision researchers and AI practitioners automatically categorize every pixel in an image into distinct objects or regions, without needing extensive manual labels. It takes raw image datasets and outputs finely segmented images where each pixel is assigned a semantic class. This is ideal for those working on machine vision tasks like autonomous driving or medical image analysis.
No commits in the last 6 months.
Use this if you need to perform semantic segmentation on large image datasets but want to minimize the time and cost associated with manual pixel-level annotation.
Not ideal if you require explainable AI or interpretability for your segmentation results, or if your dataset is very small and manual labeling is feasible.
Stars
88
Forks
7
Language
Python
License
MIT
Category
Last pushed
Oct 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hynnsk/HP"
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.