EVENT

Talk by Prof. Atsuto Maki on Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

Title:

Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

Absract:

We discuss Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. It is an application of FixMatch enabled beyond image classification by adding a matching operation on the pseudo-labels. This allows us to still use the full strength of data augmentation pipelines, including geometric transformations.
We evaluated it on semi-supervised semantic segmentation on Cityscapes and Pascal VOC with different percentages of labeled data, and ablated design choices and hyper-parameters. Dense FixMatch significantly improves results compared to supervised learning using only labeled data, approaching its performance with 1/4 of the labeled samples.
In the talk we will also brief some other related activities from our school if time permits.

Speaker:

Prof. Atsuto Maki, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology

Time/Date:

16:00 - 17:00 / Wednesday, May 10th, 2023

Place:

Onsite(NII, National Institute of Informatics)