Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/macillas/pytorch-unsupervised-segmentation-tip

https://github.com/macillas/pytorch-unsupervised-segmentation-tip

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (3.7%) to scientific vocabulary
Last synced: 5 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: MACILLAS
  • License: mit
  • Default Branch: master
  • Size: 2.3 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Fork of kanezaki/pytorch-unsupervised-segmentation-tip
Created about 5 years ago · Last pushed about 5 years ago

https://github.com/MACILLAS/pytorch-unsupervised-segmentation-tip/blob/master/ 

# Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering

This pytorch code generates segmentation labels of an input image.

![Unsupervised Image Segmentation with Scribbles](https://kanezaki.github.io/media/unsupervised_image_segmentation_with_scribbles.png)

Wonjik Kim\*, Asako Kanezaki\*, and Masayuki Tanaka.
**Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering.** 
*IEEE Transactions on Image Processing*, accepted, 2020.
([arXiv](https://arxiv.org/abs/2007.09990))

\*W. Kim and A. Kanezaki contributed equally to this work.

## What is new?

This is an extension of our [previous work](https://github.com/kanezaki/pytorch-unsupervised-segmentation). 

- Better performance with spatial continuity loss
- Option of using scribbles as user input
- Option of using reference image(s)

## Requirements

pytorch, opencv2, tqdm

## Getting started

### Vanilla

    $ python demo.py --input ./BSD500/101027.jpg

### Vanilla + scribbles

    $ python demo.py --input ./PASCAL_VOC_2012/2007_001774.jpg --scribble

### Vanilla + reference image(s)

    $ python demo_ref.py --input ./BBC/

Owner

  • Login: MACILLAS
  • Kind: user
  • Location: Waterloo, Ontario-
  • Company: CViSS Lab, Civil and Environmental Engineering, UWaterloo

GitHub Events

Total
Last Year