June 10, 2020

Our Vision and Learning lab won 1st place at WSOL, 2nd place at WSSS of LID challenge 2020.

Our Vision and Learning lab recently won 1st place at WSOL, 2nd place at WSSS of LID challenge 2020.
Prof. Gunhee Kim's team (Postdoctoral Researcher Junhyug Noh, Researcher Wonho Bae and Researcher Jinhwan Seo) participated in the Learning from Imperfect Data (LID) competition held at the CVPR 2020 with the support of Baidu.
In the challenge, we won the Weakly-supervised Object Localization (WSOL) section of the picture given, and the runner-up in the Weakly-supervised Semantic Segmentation (WSSS) section, winning 2,000 USD.
Weakness learning aims to achieve the level of supervised learning given full information even if only a part of the label is given in the learning process.    
Further details can be found at https://lidchallenge.github.io.
Relating slides can be found at Slide.