Associative Domain Adaptation
Haeusser P, Frerix T, Mordvintsev A, Cremers D (2017)
Publication Type: Conference contribution
Publication year: 2017
Publisher: Institute of Electrical and Electronics Engineers Inc.
Book Volume: 2017-October
Pages Range: 2784-2792
Conference Proceedings Title: Proceedings of the IEEE International Conference on Computer Vision
Event location: Venice, ITA
ISBN: 9781538610329
Abstract
We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source domain. Our training scheme follows the paradigm that in order to effectively derive class labels for the target domain, a network should produce statistically domain invariant embeddings, while minimizing the classification error on the labeled source domain. We accomplish this by reinforcing associations between source and target data directly in embedding space. Our method can easily be added to any existing classification network with no structural and almost no computational overhead. We demonstrate the effectiveness of our approach on various benchmarks and achieve state-of-the-art results across the board with a generic convolutional neural network architecture not specifically tuned to the respective tasks. Finally, we show that the proposed association loss produces embeddings that are more effective for domain adaptation compared to methods employing maximum mean discrepancy as a similarity measure in embedding space.
Involved external institutions
Germany (DE)
United States (USA) (US)How to cite
APA:
Haeusser, P., Frerix, T., Mordvintsev, A., & Cremers, D. (2017). Associative Domain Adaptation. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2784-2792). Venice, ITA: Institute of Electrical and Electronics Engineers Inc..
MLA:
Haeusser, Philip, et al. "Associative Domain Adaptation." Proceedings of the 16th IEEE International Conference on Computer Vision, ICCV 2017, Venice, ITA Institute of Electrical and Electronics Engineers Inc., 2017. 2784-2792.
BibTeX: Download