336x280(권장), 300x250(권장), 250x250, 200x200 크기의 광고 코드만 넣을 수 있습니다.
A pretext task is used in self-supervised learning to generate useful feature representations, where “useful” means a representation that should be easily adaptable for other tasks, unknown during training time.
Pretext Task: Pretext tasks are pre-designed tasks for networks to solve, and visual features are learned by learning objective functions of pretext tasks.
https://stats.stackexchange.com/questions/404602/pretext-task-in-computer-vision
'AI > CV & SSL' 카테고리의 다른 글
[개념정리] downstream task란? (0) | 2019.11.07 |
---|---|
[개념정리] co-adaptation이란? (0) | 2019.11.01 |
[개념정리] Ablation Study 란? (0) | 2019.10.31 |
[개념정리] Generalization & Optimization (0) | 2019.10.30 |
[개념정리] 과적합이란? (0) | 2019.09.20 |