Title: Label-efficient panoptic segmentation
Abstract: Panoptic segmentation provides a comprehensive understanding of visual scenes by assigning each pixel a semantic class label and, for objects, an instance ID. While highly effective, traditional methods rely heavily on large-scale annotated datasets, posing significant challenges for scalability and adaptability. Additionally, the process of annotating images with panoptic labels is both labor-intensive and time-consuming, highlighting the importance of label-efficient approaches. In this talk, I will present an overview of various label-efficient methods, focusing on my recent work in unsupervised domain adaptation and semi-supervised learning. I will also discuss the emerging field of open-vocabulary panoptic segmentation, which extends recognition capabilities to categories beyond the training taxonomy.
Lecturer: Josip Šarić, PhD
Short info on the lecturer: Josip Šarić is a postdoctoral researcher at the Faculty of Computer and Information Science, University of Ljubljana, supported by the SMASH postdoctoral program. Prior to this, he completed a PhD and two-year postdoc at the Faculty of Electrical Engineering and Computing, University of Zagreb. His research interests focus on computer vision and deep learning, with a particular emphasis on topics such as panoptic segmentation, open-vocabulary recognition, label-efficient learning, and related areas.
Information on AI@JSI seminars and previous recordings are available here: https://kt.ijs.si/aijsi-seminar/.
E8 - Department of Knowledge Technologies