all AI news
Weakly-supervised continual learning for class-incremental segmentation. (arXiv:2201.01029v1 [cs.CV])
Jan. 5, 2022, 2:10 a.m. | Gaston Lenczner, Adrien Chan-Hon-Tong, Nicola Luminari, Bertrand Le Saux
cs.CV updates on arXiv.org arxiv.org
Transfer learning is a powerful way to adapt existing deep learning models to
new emerging use-cases in remote sensing. Starting from a neural network
already trained for semantic segmentation, we propose to modify its label space
to swiftly adapt it to new classes under weak supervision. To alleviate the
background shift and the catastrophic forgetting problems inherent to this form
of continual learning, we compare different regularization terms and leverage a
pseudo-label strategy. We experimentally show the relevance of our …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Bosch Group | San Luis Potosí, Mexico
DATA Engineer (H/F)
@ Renault Group | FR REN RSAS - Le Plessis-Robinson (Siège)
Advisor, Data engineering
@ Desjardins | 1, Complexe Desjardins, Montréal
Data Engineer Intern
@ Getinge | Wayne, NJ, US
Software Engineer III- Java / Python / Pyspark / ETL
@ JPMorgan Chase & Co. | Jersey City, NJ, United States
Lead Data Engineer (Azure/AWS)
@ Telstra | Telstra ICC Bengaluru