| Seznam |
| Téma: | Rozpoznávání objektů v simulovaném prostředí |
|---|---|
| Katedra: | Katedra kybernetiky |
| Vedoucí: | doc. Ing. Tomáš Pajdla, Ph.D. |
| Vypsáno jako: | Bakalářská práce, Semestrální projekt |
| Popis: | Collect a set of objects that can and can't be recognized by a state of the art recognition/semantic segmentation method. Investigate and describe how the recognition behaves in a state of the art simulation. Suggest and demonstrate a technique for detecting unkonw classes. |
| Literatura: | 1) Bayesian Semantic Instance Segmentation in Open Set World https://arxiv.org/pdf/1806.00911.pdf
2) The Importance of Metric Learning for Robotic Vision: Open Set Recognition and Active Learning https://arxiv.org/pdf/1902.10363.pdf 3) Recent Advances in Open Set Recognition: A Survey https://arxiv.org/pdf/1811.08581.pdf 4) YOLACT Real-time Instance Segmentation. https://openaccess.thecvf.com/content_ICCV_2019/papers/Bolya_YOLACT_Real-Time_Instance_Segmentation_ICCV_2019_paper.pdf |