Corpus ID: 3648559

Joint Pixel and Feature-level Domain Adaptation in the Wild

  title={Joint Pixel and Feature-level Domain Adaptation in the Wild},
  author={L. Tran and Kihyuk Sohn and X. Yu and X. Liu and Manmohan Chandraker},
  • L. Tran, Kihyuk Sohn, +2 authors Manmohan Chandraker
  • Published 2018
  • Computer Science
  • ArXiv
  • Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels. We propose that advantages may be derived by combining them, in the form of different insights that lead to a novel design and complementary properties that result in better performance. At the feature level, inspired by insights from semi-supervised learning in a domain adversarial neural network, we… CONTINUE READING
    2 Citations
    Joint Feature-level and Pixel-level Domain Adaption for Object Detection in the Wild
    • Qianhui Luo, Yue Wang, Weijie Li, R. Xiong
    • Computer Science
    • 2019 IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER)
    • 2019
    Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation
    • Jinghua Wang, J. Jiang
    • Computer Science
    • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
    • 2019
    • 7
    • PDF


    Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
    • 809
    • PDF
    CyCADA: Cycle-Consistent Adversarial Domain Adaptation
    • 1,022
    • PDF
    Domain-Adversarial Training of Neural Networks
    • 2,884
    • Highly Influential
    • PDF
    Unsupervised Cross-Domain Image Generation
    • 590
    • PDF
    Learning from Simulated and Unsupervised Images through Adversarial Training
    • 1,109
    • PDF
    Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos
    • 70
    • PDF
    Towards Large-Pose Face Frontalization in the Wild
    • 183
    • PDF
    Associative Domain Adaptation
    • 153
    • PDF
    Improved Techniques for Training GANs
    • 3,947
    • Highly Influential
    • PDF
    Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
    • 249
    • PDF