Mhpl: Minimum happy points learning for active source free domain adaptation
Source free domain adaptation (SFDA) aims to transfer a trained source model to the
unlabeled target domain without accessing the source data. However, the SFDA setting …
unlabeled target domain without accessing the source data. However, the SFDA setting …
[PDF][PDF] MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation
F Wang, Z Han, Z Zhang, R He, Y Yin - openaccess.thecvf.com
Methods (3),(4), and (5) are based on model uncertainty,(6) and (7) are diversity-based, and
(8) is a hybrid approach that combines uncertainty and diversity. Regarding implementation …
(8) is a hybrid approach that combines uncertainty and diversity. Regarding implementation …
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation
F Wang, Z Han, Z Zhang, R He, Y Yin - 2023 IEEE/CVF Conference on …, 2023 - computer.org
Source free domain adaptation (SFDA) aims to transfer a trained source model to the
unlabeled target domain without accessing the source data. However, the SFDA setting …
unlabeled target domain without accessing the source data. However, the SFDA setting …
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation
F Wang, Z Han, Z Zhang, R He… - 2023 IEEE/CVF …, 2023 - ieeexplore.ieee.org
Source free domain adaptation (SFDA) aims to transfer a trained source model to the
unlabeled target domain without accessing the source data. However, the SFDA setting …
unlabeled target domain without accessing the source data. However, the SFDA setting …