Tune It the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density
Authors
Authors
- Kuniaki Saito
- Donghyun Kim
- Piotr Teterwak
- Stan Sclaroff
- Trevor Darrell
- Kate Saenko
Authors
- Kuniaki Saito
- Donghyun Kim
- Piotr Teterwak
- Stan Sclaroff
- Trevor Darrell
- Kate Saenko
Published on
10/17/2021
Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achieving high accuracy and avoiding negative transfer. Supervised hyper-parameter validation is not possible without labeled target data, which raises the question: How can we validate unsupervised adaptation techniques in a realistic way? We first empirically analyze existing criteria and demonstrate that they are not very effective for tuning hyper-parameters. Intuitively, a well-trained source classifier should embed target samples of the same class nearby, forming dense neighborhoods in feature space. Based on this assumption, we propose a novel unsupervised validation criterion that measures the density of soft neighborhoods by computing the entropy of the similarity distribution between points. Our criterion is simpler than competing validation methods, yet more effective; it can tune hyper-parameters and the number of training iterations in both image classification and semantic segmentation models.
Please cite our work using the BibTeX below.
@InProceedings{Saito_2021_ICCV,
author = {Saito, Kuniaki and Kim, Donghyun and Teterwak, Piotr and Sclaroff, Stan and Darrell, Trevor and Saenko, Kate},
title = {Tune It the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2021},
pages = {9184-9193}
}