Transferable Representation Learning with Deep Adaptation Networks

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 41; no. 12; pp. 3071 - 3085
• Main Authors: Long, Mingsheng, Cao, Yue, Cao, Zhangjie, Wang, Jianmin, Jordan, Michael I.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Algorithms; Artificial neural networks; convolutional neural network; Convolutional neural networks; Deep learning; Domain adaptation; Domains; Hilbert space; Kernels; Learning systems; Machine learning; Minimax technique; multiple kernel learning; Neural networks; Task analysis; two-sample test
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2018.2868685

Domain adaptation studies learning algorithms that generalize across source domains and target domains that exhibit different distributions. Recent studies reveal that deep neural networks can learn transferable features that generalize well to similar novel tasks. However, as deep features eventually transition from general to specific along the network, feature transferability drops significantly in higher task-specific layers with increasing domain discrepancy. To formally reduce the effects of this discrepancy and enhance feature transferability in task-specific layers, we develop a novel framework for deep adaptation networks that extends deep convolutional neural networks to domain adaptation problems. The framework embeds the deep features of all task-specific layers into reproducing kernel Hilbert spaces (RKHSs) and optimally matches different domain distributions. The deep features are made more transferable by exploiting low-density separation of target-unlabeled data in very deep architectures, while the domain discrepancy is further reduced via the use of multiple kernel learning that enhances the statistical power of kernel embedding matching. The overall framework is cast in a minimax game setting. Extensive empirical evidence shows that the proposed networks yield state-of-the-art results on standard visual domain-adaptation benchmarks.