• Home
  • Search
  • Transferable Representation Learning with Deep Adaptation Networks.
  • Cite Icon706
  • https://doi.org/10.1109/tpami.2018.2868685Copy DOI Icon

Transferable Representation Learning with Deep Adaptation Networks.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

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.

Similar Papers
  • PDF
  • Research Article
  • Citations47

C2DAN: An Improved Deep Adaptation Network with Domain Confusion and Classifier Adaptation.

  • Jun 26, 2020
  • Sensors
  • Han Sun +5
  • Research Article
  • Citations7

Deep domain similarity Adaptation Networks for across domain classification

  • Aug 07, 2018
  • Pattern Recognition Letters
  • Yu Chen +2
  • Research Article
  • Citations17

Domain-invariant representation learning using an unsupervised domain adversarial adaptation deep neural network

  • May 10, 2019
  • Neurocomputing
  • Xibin Jia +3
  • Research Article
  • Citations45

Deep Feature Alignment Neural Networks for Domain Adaptation of Hyperspectral Data

  • Oct 01, 2018
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xiong Zhou +1
  • Research Article
  • Citations5

Encrypted Traffic Classification Through Deep Domain Adaptation Network With Smooth Characteristic Function

  • Feb 01, 2025
  • IEEE Transactions on Network and Service Management
  • Van Tong +6
  • Conference Article
  • Citations9

An Adaptive Localization Approach Based on Deep Adaptation Networks

  • Oct 01, 2019
  • Lei Wang +2
  • Research Article
  • Citations4

Semi-supervised graph convolutional networks for the domain adaptive recognition of thyroid nodules in cross-device ultrasound images.

  • Apr 06, 2023
  • Medical Physics
  • Kun Zhang +9
  • Research Article
  • Citations62

Geometric Knowledge Embedding for unsupervised domain adaptation

  • Oct 25, 2019
  • Knowledge-Based Systems
  • Hanrui Wu +4
  • Dissertation
  • Citations1

Domain Adaptation and Domain Generalization with Representation Learning

  • Jan 01, 2016
  • Muhammad Ghifary
  • Dissertation
  • Citations2

Domain Adaptation and Domain Generalization with Representation Learning

  • Jan 01, 2016
  • Muhammad Ghifary
  • Research Article
  • Citations3

Robust Deep Softmax Regression Against Label Noise for Unsupervised Domain Adaptation

  • Jun 07, 2019
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Guangbin Wu +4
  • Dissertation

Towards robust sensing and recognition : from statistical learning to transfer learning

  • Jan 01, 2020
  • Jianfei Yang
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Research Article
  • Citations2

Unsupervised classification based on deep adaptation network for sonar images

  • Feb 13, 2023
  • Journal of Electronic Imaging
  • Huipu Xu +2
  • Research Article
  • Citations52

Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation

  • Apr 25, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Daixin Wang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.