Benutzer: Gast  Login
Titel:

Multi-Task Consistency for Active Learning

Dokumenttyp:
Konferenzbeitrag
Autor(en):
Hekimoglu, Aral; Friedrich, Philipp; Zimmer, Walter; Schmidt, Michael; Marcos-Ramiro, Alvaro; Knoll, Alois
Abstract:
Learning-based solutions for vision tasks require a large amount of labeled training data to ensure their performance and reliability. In single-task vision-based settings, inconsistency-based active learning has proven to be effective in selecting informative samples for annotation. However, there is a lack of research exploiting the inconsistency between multiple tasks in multi-task networks. To address this gap, we propose a novel multi-task active learning strategy for two coupled vision tas...     »
Kongress- / Buchtitel:
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Verlag / Institution:
IEEE
Publikationsdatum:
02.10.2023
Jahr:
2023
Volltext / DOI:
doi:10.1109/iccvw60793.2023.00366
WWW:
https://ieeexplore.ieee.org/document/10350950
 BibTeX