• Home
  • Search
  • Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
  • Open Access IconOpen Access
  • Cite Icon692
  • https://doi.org/10.1109/cvpr.2017.107Copy DOI Icon

Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation

  • Jul 1, 2017
  • Hongliang Yan +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In domain adaptation, maximum mean discrepancy (MMD) has been widely adopted as a discrepancy metric between the distributions of source and target domains. However, existing MMD-based domain adaptation methods generally ignore the changes of class prior distributions, i.e., class weight bias across domains. This remains an open problem but ubiquitous for domain adaptation, which can be caused by changes in sample selection criteria and application scenarios. We show that MMD cannot account for class weight bias and results in degraded domain adaptation performance. To address this issue, a weighted MMD model is proposed in this paper. Specifically, we introduce class-specific auxiliary weights into the original MMD for exploiting the class prior probability on source and target domains, whose challenge lies in the fact that the class label in target domain is unavailable. To account for it, our proposed weighted MMD model is defined by introducing an auxiliary weight for each class in the source domain, and a classification EM algorithm is suggested by alternating between assigning the pseudo-labels, estimating auxiliary weights and updating model parameters. Extensive experiments demonstrate the superiority of our weighted MMD over conventional MMD for domain adaptation.

Similar Papers
  • Book Chapter
  • Citations1

The $$\ell _{2,1}$$-Norm Stacked Robust Autoencoders via Adaptation Regularization for Domain Adaptation

  • Jan 01, 2019
  • Shuai Yang +4
  • Conference Article
  • Citations3

Modeling Sequential Domain Shift through Estimation of Optimal Sub-spaces for Categorization

  • Jan 01, 2014
  • Suranjana Samanta +2
  • Research Article
  • Citations15

Discriminative and domain invariant subspace alignment for visual tasks

  • Jun 03, 2019
  • Iran Journal of Computer Science
  • Samaneh Rezaei +1
  • 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
  • Research Article
  • Citations113

Weighted and Class-Specific Maximum Mean Discrepancy for Unsupervised Domain Adaptation

  • Nov 22, 2019
  • IEEE Transactions on Multimedia
  • Hongliang Yan +5
  • Research Article
  • Citations49

An Evidential Multi-Target Domain Adaptation Method Based on Weighted Fusion for Cross-Domain Pattern Classification.

  • Oct 01, 2024
  • IEEE transactions on neural networks and learning systems
  • Linqing Huang +5
  • PDF
  • Research Article
  • Citations11

An Improved Hybrid Transfer Learning-Based Deep Learning Model for PM2.5 Concentration Prediction

  • Apr 01, 2022
  • Applied Sciences
  • Jianjun Ni +4
  • Research Article
  • Citations36

Unsupervised Domain Adaptation by Matching Distributions Based on the Maximum Mean Discrepancy via Unilateral Transformations

  • Jul 17, 2019
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Atsutoshi Kumagai +1
  • Research Article
  • Citations2

Discriminative possibilistic clustering promoting cross-domain emotion recognition.

  • Nov 01, 2024
  • Frontiers in neuroscience
  • Yufang Dan +2
  • Research Article
  • Citations63

Improved Techniques for Adversarial Discriminative Domain Adaptation.

  • Nov 06, 2019
  • IEEE Transactions on Image Processing
  • Aaron Chadha +1
  • Research Article
  • Citations141

Intelligent Fault Diagnosis Under Varying Working Conditions Based on Domain Adaptive Convolutional Neural Networks

  • Jan 01, 2018
  • IEEE Access
  • Bo Zhang +3
  • Research Article
  • Citations51

A MultiKernel Domain Adaptation Method for Unsupervised Transfer Learning on Cross-Source and Cross-Region Remote Sensing Data Classification

  • Jan 17, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Wei Liu +1
  • Research Article
  • Citations16

Overcoming learning bias via Prototypical Feature Compensation for source-free domain adaptation

  • Sep 17, 2024
  • Pattern Recognition
  • Zicheng Pan +3
  • Conference Article
  • Citations9

Domain transfer nonnegative matrix factorization

  • Jul 01, 2014
  • Jim Jing-Yan Wang +2
  • Research Article
  • Citations25

A New Progressive Multisource Domain Adaptation Network With Weighted Decision Fusion.

  • Jan 01, 2024
  • IEEE Transactions on Neural Networks and Learning Systems
  • Zhun-Ga Liu +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.