Multi-task multi-objective evolutionary network for hyperspectral image classification and pansharpening

•A multi-task multi-objective evolutionary network is proposed.•The framework combines two tasks by effective high-frequency information sharing.•Multi-task learning is modeled as a deep MOEAD to obtain trade-off solutions.•The method provides diverse and sufficient samples for multi-task. Multi-tas...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Information fusion Ročník 108; s. 102383
Hlavní autoři: Wu, Xiande, Feng, Jie, Shang, Ronghua, Wu, JinJian, Zhang, Xiangrong, Jiao, Licheng, Gamba, Paolo
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.08.2024
Témata:
Hyperspectral classification
Hyperspectral pansharpening
Multi-objective evolution algorithm
Multi-task learning
Multi-objective evolution algorithm
Hyperspectral pansharpening
Multi-task learning
Hyperspectral classification
ISSN:1566-2535, 1872-6305
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•A multi-task multi-objective evolutionary network is proposed.•The framework combines two tasks by effective high-frequency information sharing.•Multi-task learning is modeled as a deep MOEAD to obtain trade-off solutions.•The method provides diverse and sufficient samples for multi-task. Multi-task learning has commonly been used and performed well at joint visual perception tasks. Hyperspectral pansharpening (HP) and hyperspectral classification (HC) tasks extract high-frequency information to enhance edges and classify samples, offering potential for performance improvements in multi-task learning. However, differences between tasks can make it challenging to balance their performances. To address this challenge, this paper proposes a multi-task multi-objective evolutionary network (DMOEAD) for joint learning of HC and HP. A multi-task sufficiency-and-diversity sampling method is designed to unify the heterogeneity of sample construction between two types of tasks. Two types of task-specific networks are constructed to decompose high-frequency information. Further, a collaborative learning module is designed to dynamically learn complementary high-frequency information from another task in different layers. To be compatible with the optimization direction of two types of tasks, multi-task optimization is realized using a deep multi-objective evolutionary algorithm (DMEO). In the DMEO, the set of parameters of the DMOEAD is regarded as an individual. A deep mutation operator is designed and used for network optimization, which accelerates large-scale network parameter searching. The DMEO can coordinate the differences between multiple tasks and provide a set of Pareto network parameter solutions. Finally, the experimental results demonstrate that the proposed method can significantly enhance the performance of both pansharpening and classification tasks.
ISSN:1566-2535
1872-6305
DOI:10.1016/j.inffus.2024.102383