Multi-task self-supervised visual learning
We investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling-in order to train a single visual representation. First, we provide an apples-to-apples comparison of four different self-supervised tasks using the very dee...
Автори: | Doersch, C, Zisserman, A |
---|---|
Формат: | Conference item |
Опубліковано: |
IEEE Explore
2017
|
Схожі ресурси
Схожі ресурси
-
Self-supervised learning of audio-visual objects from video
за авторством: Afouras, T, та інші
Опубліковано: (2020) -
Multi-Task Collaborative Network: Bridge the Supervised and Self-Supervised Learning for EEG Classification in RSVP Tasks
за авторством: Hongxin Li, та інші
Опубліковано: (2024-01-01) -
Sim2real transfer learning for 3D human pose estimation: motion to the rescue
за авторством: Doersch, C, та інші
Опубліковано: (2020) -
Self-supervised learning for spinal MRIs
за авторством: Jamaludin, A, та інші
Опубліковано: (2017) -
Self-supervised multi-task representation learning for sequential medical images
за авторством: Dong, N, та інші
Опубліковано: (2021)