Addressing the cold start problem in active learning using self-supervised learning
Active learning promises to improve annotation efficiency by iteratively selecting the most important data to be annotated first. However, we uncover a striking contrast to this promise: Active querying strategies fail to select data as effectively as random selection at the first choice. We identif...
Saved in:
主要作者: | Chen, Liangyu |
---|---|
其他作者: | Wen Bihan |
格式: | Final Year Project |
語言: | English |
出版: |
Nanyang Technological University
2022
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/158461 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
WiFi and vision multimodal self-supervised learning for human activity recognition
由: Tang, Shijie
出版: (2023) -
Mining visual collocation patterns via self-supervised subspace learning
由: Yuan, Junsong, et al.
出版: (2013) -
Stock trading and prediction using weakly supervised learning
由: Tan, Nigel Jun Wen
出版: (2021) -
Geometry guided supervised representation learning for classification
由: Li, Yue
出版: (2020) -
Self-supervised online metric learning with low rank constraint for scene categorization
由: Cong, Yang, et al.
出版: (2013)