• Home
  • Search
  • Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation.
  • Cite Icon59
  • https://doi.org/10.1109/tpami.2019.2962476Copy DOI Icon

Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation.

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

This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategies for training the neural network. The domain-collaborative learning strategy aims to learn domain specific feature representation to preserve the discriminability for the target domain, while the domain adversarial learning strategy aims to learn domain invariant feature representation to reduce the domain distribution mismatch between the source and target domains. We show that these two learning strategies can be uniformly formulated as domain classifier learning with positive or negative weights on the losses. We then design a collaborative and adversarial training scheme, which automatically learns domain specific representations from lower blocks in CNNs through collaborative learning and domain invariant representations from higher blocks through adversarial learning. Moreover, to further enhance the discriminability in the target domain, we propose Self-Paced CAN (SPCAN), which progressively selects pseudo-labeled target samples for re-training the classifiers. We employ a self-paced learning strategy such that we can select pseudo-labeled target samples in an easy-to-hard fashion. Additionally, we build upon the popular two-stream approach to extend our domain adaptation approach for more challenging video action recognition task, which additionally considers the cooperation between the RGB stream and the optical flow stream. We propose the Two-stream SPCAN (TS-SPCAN) method to select and reweight the pseudo labeled target samples of one stream (RGB/Flow) based on the information from the other stream (Flow/RGB) in a cooperative way. As a result, our TS-SPCAN model is able to exchange the information between the two streams. Comprehensive experiments on different benchmark datasets, Office-31, ImageCLEF-DA and VISDA-2017 for the object recognition task, and UCF101-10 and HMDB51-10 for the video action recognition task, show our newly proposed approaches achieve the state-of-the-art performance, which clearly demonstrates the effectiveness of our proposed approaches for unsupervised domain adaptation.

Similar Papers
  • Research Article
  • Citations5

A two-layer regression network for robust and accurate domain adaptation

  • Sep 23, 2024
  • Pattern Recognition
  • Geonseok Lee +1
  • Conference Article
  • Citations10

Transferable Feature Learning on Graphs Across Visual Domains

  • Jul 05, 2021
  • Ronghang Zhu +3
  • Research Article
  • Citations33

Cross-Domain Graph Convolutions for Adversarial Unsupervised Domain Adaptation.

  • Aug 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Ronghang Zhu +3
  • Research Article
  • Citations14

Unsupervised deep domain adaptation algorithm for video based human activity recognition via recurrent neural networks

  • Jul 07, 2024
  • Engineering Applications of Artificial Intelligence
  • Abdulaziz Zam +2
  • Research Article
  • Citations77

Margin Preserving Self-Paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation.

  • Feb 01, 2022
  • IEEE Journal of Biomedical and Health Informatics
  • Zhizhe Liu +5
  • Book Chapter
  • Citations69

Graph Matching and Pseudo-Label Guided Deep Unsupervised Domain Adaptation

  • Jan 01, 2018
  • Debasmit Das +1
  • Research Article
  • Citations734

Wasserstein Distance Guided Representation Learning for Domain Adaptation

  • Apr 29, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Jian Shen +3
  • Book Chapter
  • Citations21

Adversarial Continuous Learning in Unsupervised Domain Adaptation

  • Jan 01, 2021
  • Youshan Zhang +1
  • Video Transcripts

Adversarial Continuous Learning in Unsupervised Domain Adaptation

  • Jan 15, 2020
  • Underline Science Inc.
  • Brian Davison +1
  • Conference Article
  • Citations1

Gaussian Mixture Model for Graph Domain Adaptation

  • Sep 01, 2025
  • Mengzhu Wang +6
  • Research Article
  • Citations5

Unsupervised Domain Adaptative SAR Target Detection Based on Feature Decomposition and Uncertainty-Guided Self-Training

  • Jan 01, 2024
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Yu Shi +4
  • Conference Article
  • Citations225

Duplex Generative Adversarial Network for Unsupervised Domain Adaptation

  • Jun 01, 2018
  • Lanqing Hu +3
  • Research Article
  • Citations4

Domain Adaptation via Bregman divergence minimization

  • Jul 07, 2021
  • Scientia Iranica
  • Mozhdeh Zandifar +2
  • Research Article
  • Citations60

Domain Adaptation for Remote Sensing Image Semantic Segmentation: An Integrated Approach of Contrastive Learning and Adversarial Learning

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Lubin Bai +5
  • Conference Article

Robust Domain Adaptation: Representations, Weights and Inductive Bias (Extended Abstract)

  • Aug 01, 2021
  • Victor Bouvier +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.