| Title |
Label-efficient Learning Methods for Computer Vision Applications |
| Authors |
(Moon Ye-Bin);(Tae-Hyun Oh) |
| DOI |
https://doi.org/10.5573/IEIESPC.2024.13.2.120 |
| Keywords |
Label-efficient learning; Synthetic data; Heterogeneous datasets; Transfer learning; Self-supervised learning; Semi-supervised learning; Computer vision |
| Abstract |
In this work, we review the challenges of data scarcity and label inefficiency in deep learning and survey efforts to overcome these challenges. Many label-efficient learning methods have been proposed, but there is still room to develop more effective methods. We introduce potential yet promising directions to achieve label-efficient learning in terms of data, learning methods, and efficient use of prior knowledge. We also present case studies involving the latest methods. |