philferriere/tfwss
Weakly Supervised Segmentation with Tensorflow. Implements instance segmentation as described in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017).
This project helps computer vision practitioners create detailed image segmentation masks without the extensive effort of pixel-by-pixel labeling. You provide an image and rough bounding boxes around objects, and it generates precise segmentation masks for each instance. This tool is for researchers and developers in computer vision who need to train models for tasks like object recognition or scene understanding, but want to significantly reduce the cost and time associated with data annotation.
221 stars. No commits in the last 6 months.
Use this if you need to train instance segmentation models but want to leverage cheaper bounding box annotations instead of expensive pixel-level masks.
Not ideal if you require 100% human-annotated pixel-perfect ground truth masks for your training data.
Stars
221
Forks
48
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 15, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/philferriere/tfwss"
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.