Detail of the student project

List
Topic:Multiview Object Open-Set Classification
Department:Katedra kybernetiky
Supervisor:doc. Ing. Tomáš Pajdla, Ph.D.
Announce as:Diplomová práce, Semestrální projekt
Description:1) Review the literature [1,2,3] and select the most promising method for multiview object open-set classification.
2) Find a dataset to evaluate the most promising method.
3) Summarize the experiment and explain the behavior of the best method on the multi-view data.
Bibliography:[1] Silvio Galesso, Max Argus, Thomas Brox. Far Away in the Deep Space: Nearest-Neighbor-Based Dense Out-of-Distribution Detection. arXiv:2211.06660
[2] Sagar Vaze, Kai Han, Andrea Vedaldi, Andrew Zisserman. Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
arXiv:2110.06207
[3] Marco Seeland, Patrick Mäder. Multi-view classification with convolutional neural networks. PLOS ONE 16(1): https://doi.org/10.1371/journal.pone.0245230
Responsible person: Petr Pošík