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:
Main Author: | Chen, Liangyu |
---|---|
Other Authors: | Wen Bihan |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/158461 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
WiFi and vision multimodal self-supervised learning for human activity recognition
by: Tang, Shijie
Published: (2023) -
Mining visual collocation patterns via self-supervised subspace learning
by: Yuan, Junsong, et al.
Published: (2013) -
Stock trading and prediction using weakly supervised learning
by: Tan, Nigel Jun Wen
Published: (2021) -
Self-supervised and supervised contrastive learning
by: Tan, Alvin De Jun
Published: (2023) -
Geometry guided supervised representation learning for classification
by: Li, Yue
Published: (2020)