https://scholars.lib.ntu.edu.tw/handle/123456789/629899
標題: | Improving Clustering Uncertainty-weighted Embeddings for Active Domain Adaptation | 作者: | Wu, Sheng Feng HSUAN-TIEN LIN |
關鍵字: | active learning | domain adaptation | 公開日期: | 1-一月-2022 | 來源出版物: | Proceedings - 2022 International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2022 | 摘要: | Domain adaptation generalizes deep neural networks to new target domains under domain shift. Active domain adaptation (ADA) does so efficiently by allowing the learning model to strategically ask data annotation questions. The state-of-the-art active domain adaptation via clustering uncertainty-weighted embeddings (ADA-CLUE) uses uncertainty-weighted clustering to identify target instances for labeling. In this work, we carefully study how ADA-CLUE balances uncertainty and diversity during active learning. We compare the original ADA-CLUE with a variant that weights clusters by a constant instead of by the uncertainty, and confirm that constant-weighted clustering sampling outperforms ADA-CLUE at early stages due to its stability. We then merge constant-weighted sampling and uncertainty-weighted sampling with a threshold to get the best of the two worlds. The merged solution, called CLUE with a loop threshold, is shown to be an empirically better choice than the original ADA-CLUE. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/629899 | ISBN: | 9798350399509 | DOI: | 10.1109/TAAI57707.2022.00013 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。