Detail of the student project

List
Topic:Kalibrace pravděpodobnostních klasifikátorů nad rámec top-1 predikce
Department: Skupina vizuálního rozpoznávání
Supervisor:prof. Ing. Jiří Matas, Ph.D.
Announce as:Diplomová práce, Bakalářská práce, Semestrální projekt
Description:Použijte Google Translate na anglické zadání.
Bibliography:[1] Guo, Chuan, et al. "On calibration of modern neural networks." International Conference on Machine Learning. PMLR, 2017.Guo, Chuan, et al. "On calibration of modern neural networks." International Conference on Machine Learning. PMLR, 2017.
[2] Alexandari, Amr, Anshul Kundaje, and Avanti Shrikumar. "Maximum likelihood with bias-corrected calibration is hard-to-beat at label shift adaptation." International Conference on Machine Learning. PMLR, 2020.
[3] Sipka, Tomas, Milan Sulc, and Jiri Matas. "The Hitchhiker's Guide to Prior-Shift Adaptation." arXiv preprint arXiv:2106.11695 (2021).
[4] Vaicenavicius, Juozas, et al. "Evaluating model calibration in classification." The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 2019.
[5] Kumar, Aviral, Sunita Sarawagi, and Ujjwal Jain. "Trainable calibration measures for neural networks from kernel mean embeddings." International Conference on Machine Learning. PMLR, 2018.
Responsible person: Petr Pošík