Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings
2021-10-10
Generalizing deep neural networks to new target domains is critical to their real-world utility. While labeling data from the target domain, it is desirable to select a subset that is maximally-informative to be cost-effective (called Active Learning). The ADA-CLUE algorithm addresses the problem of Active Learning under a domain shift. The GitHub repo consists of code to train models with the ADA-CLUE algorithm for multiple source and target domain shifts. Pre-trained models are also available.
| Author(s): | Viraj Prabhu and Arjun Chandrasekaran and Kate Saenko and Judy Hoffman |
| Department(s): |
Perceiving Systems |
| Publication(s): |
Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings
|
| Authors: | Viraj Prabhu and Arjun Chandrasekaran and Kate Saenko and Judy Hoffman |
| Release Date: | 2021-10-10 |
| License: | The MIT License (MIT) |
| External Link: | https://github.com/virajprabhu/CLUE |
