WXinlong/SOLO
A PyTorch implementation of SOLO and SOLOv2, two deep learning algorithms for instance segmentation published at ECCV 2020 and NeurIPS 2020.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official PyTorch implementation of SOLO (Segmenting Objects by Locations), a box-free instance segmentation approach that directly outputs instance masks and class probabilities via fully convolutional networks. SOLOv2 improves on the original with dynamic and faster mask prediction. Both methods achieve state-of-the-art results on COCO, with the best model reaching 41.7% AP.
Frequently asked
- What is WXinlong/SOLO?
- A PyTorch implementation of SOLO and SOLOv2, two deep learning algorithms for instance segmentation published at ECCV 2020 and NeurIPS 2020.
- Is SOLO open source?
- Yes — WXinlong/SOLO is an open-source project tracked on heatdrop.
- What language is SOLO written in?
- WXinlong/SOLO is primarily written in Python.
- How popular is SOLO?
- WXinlong/SOLO has 1.8k stars on GitHub.
- Where can I find SOLO?
- WXinlong/SOLO is on GitHub at https://github.com/WXinlong/SOLO.