xuebinqin/DIS
A deep learning model for precise object-level image segmentation published at ECCV 2022.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official implementation of a dichotomous image segmentation task aimed at highly accurate foreground object extraction from images. It includes IS-Net and U-2-Net based architectures trained for general segmentation use cases, offering inference code for applying the models to custom datasets.
Frequently asked
- What is xuebinqin/DIS?
- A deep learning model for precise object-level image segmentation published at ECCV 2022.
- Is DIS open source?
- Yes — xuebinqin/DIS is open source, released under the Apache-2.0 license.
- What language is DIS written in?
- xuebinqin/DIS is primarily written in Jupyter Notebook.
- How popular is DIS?
- xuebinqin/DIS has 2.6k stars on GitHub.
- Where can I find DIS?
- xuebinqin/DIS is on GitHub at https://github.com/xuebinqin/DIS.