Multi-Label Multi-Task Learning with Dynamic Task Weight Balancing
Author
Abstract
Data collected from real-world environments often contain multiple objects, scenes, and activities. In comparison to single-label problems, where each data sample only defines one concept, multi-label problems allow the co-existence of multiple concepts. To exploit the rich semantic information in real-world data, multi-label classification has seen many applications in a variety of domains.
Year of Publication
2020
Conference Name
2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science (IRI)
Date Published
08