• Home
  • Search
  • Adversarial Bipartite Graph Learning for Video Domain Adaptation
  • Open Access IconOpen Access
  • Cite Icon46
  • https://doi.org/10.1145/3394171.3413897Copy DOI Icon

Adversarial Bipartite Graph Learning for Video Domain Adaptation

  • Oct 12, 2020
  • Yadan Luo +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Domain adaptation techniques, which focus on adapting models between distributionally different domains, are rarely explored in the video recognition area due to the significant spatial and temporal shifts across the source (i.e. training) and target (i.e. test) domains. As such, recent works on visual domain adaptation which leverage adversarial learning to unify the source and target video representations and strengthen the feature transferability are not highly effective on the videos. To overcome this limitation, in this paper, we learn a domain-agnostic video classifier instead of learning domain-invariant representations, and propose an Adversarial Bipartite Graph (ABG) learning framework which directly models the source-target interactions with a network topology of the bipartite graph. Specifically, the source and target frames are sampled as heterogeneous vertexes while the edges connecting two types of nodes measure the affinity among them. Through message-passing, each vertex aggregates the features from its heterogeneous neighbors, forcing the features coming from the same class to be mixed evenly. Explicitly exposing the video classifier to such cross-domain representations at the training and test stages makes our model less biased to the labeled source data, which in-turn results in achieving a better generalization on the target domain. To further enhance the model capacity and testify the robustness of the proposed architecture on difficult transfer tasks, we extend our model to work in a semi-supervised setting using an additional video-level bipartite graph. Extensive experiments conducted on four benchmarks evidence the effectiveness of the proposed approach over the SOTA methods on the task of video recognition.

Similar Papers
  • Conference Article
  • Citations8

Learning Target Predictive Function without Target Labels

  • Dec 01, 2012
  • Chun-Wei Seah +3
  • Research Article
  • Citations1

Domain Adaptation for Image Classification of Defects in Semiconductor Manufacturing

  • Jan 01, 2026
  • IEEE Transactions on Automation Science and Engineering
  • Adrian Poniatowski +5
  • Research Article
  • Citations4

Deep learning-based domain adaptation for a generalized detection of wear phenomena during blanking

  • Aug 01, 2023
  • Manufacturing Letters
  • Christian Kubik +3
  • Conference Article
  • Citations4

Machine Learning Pipeline for Reusing Pretrained Models

  • Nov 02, 2020
  • Maryam Alshehhi +1
  • Research Article
  • Citations8

Handling new target classes in semantic segmentation with domain adaptation

  • Aug 18, 2021
  • Computer Vision and Image Understanding
  • Maxime Bucher +3
  • Research Article
  • Citations53

Domain Adversarial Reinforcement Learning for Partial Domain Adaptation.

  • Oct 16, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Jin Chen +3
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • 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
  • Research Article
  • Citations21

Adversarial transfer learning for cross-domain visual recognition

  • Jul 15, 2020
  • Knowledge-Based Systems
  • Shanshan Wang +2
  • Conference Article

Domain adaptation by topology regularization

  • Apr 21, 2021
  • Deborah Weeks +1
  • Conference Article
  • Citations12

Partially Adversarial Learning and Adaptation

  • Sep 01, 2019
  • Jen-Tzung Chien +1
  • PDF
  • Research Article
  • Citations1

Correlation enhanced distribution adaptation for prediction of fall risk

  • Feb 12, 2024
  • Scientific Reports
  • Ziqi Guo +4
  • Research Article
  • Citations6

Cluster-based adaptive SVM: A latent subdomains discovery method for domain adaptation problems

  • Jun 10, 2017
  • Computer Vision and Image Understanding
  • Azadeh Sadat Mozafari +1
  • Conference Article
  • Citations72

Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation

  • Jun 01, 2020
  • Yingwei Pan +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.