• Home
  • Search
  • Automatic Loss Function Search for Adversarial Unsupervised Domain Adaptation
  • Cite Icon38
  • https://doi.org/10.1109/tcsvt.2023.3260246Copy DOI Icon

Automatic Loss Function Search for Adversarial Unsupervised Domain Adaptation

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

Unsupervised domain adaption (UDA) aims to reduce the domain gap between labeled source and unlabeled target domains. Many prior works exploit adversarial learning that leverages pre-designed discriminators to drive the network for aligning distributions between domains. However, most of them do not consider the degeneration of the domain discriminators caused by the gradually dominating gradients of aligned target samples during training, and they still suffer from the cross-domain semantic mismatch problem in the learned feature space. Hence, this paper attempts to understand and solve both issues from the lens of optimization loss and propose an automatic loss function search for adversarial domain adaptation (ALSDA). First, we extend the common adversarial loss by adding an adjustable hyper-parameter that can re-weight the gradients assigned to target samples, so that the domain discriminator can impose consecutive and influential driving forces for domain alignment. Meanwhile, we upgrade the traditional orthogonality loss with class-wisely adjustable hyper-parameters that can strengthen the cross-domain feature separation. Since manually determining the optimal loss functions requires expensive expert efforts, we leverage the popular AutoML to automatically search for the optimal loss functions from a pre-defined novel and unique search space for UDA. Further, to enable the loss function search when the target domain is unlabeled, we introduce a simple-but-effective entropy-guided search strategy with the aid of REINFORCE learning. Extensive experiments on various typical baselines and benchmark datasets such as Office-Home, Office-31, and Birds-31 have been conducted, and the results validate the generalization and superiority of the proposed ALSDA.

Similar Papers
  • Research Article
  • Citations5

Bridging domain gaps in agricultural 3D point cloud classification using adversarial domain adaptation

  • Nov 25, 2025
  • Scientific Reports
  • Zainab Fatima +2
  • Research Article

Adversarial Unsupervised Domain Adaptation Image Classification Method Based on Contrastive Learning

  • May 01, 2025
  • Journal of Computer-Aided Design & Computer Graphics
  • Ting Wang +3
  • Research Article
  • Citations3

AVATAR: Adversarial self-superVised domain Adaptation network for TARget domain

  • Aug 28, 2024
  • Expert Systems With Applications
  • Jun Kataoka +1
  • Conference Article
  • Citations9

Adversarial Unsupervised Domain Adaptation Guided with Deep Clustering for Face Presentation Attack Detection

  • Jan 01, 2021
  • Yomna El-Din +2
  • 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
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

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

Minimizing Outputs’ Differences of Classifiers with Different Responsibilities for Unsupervised Adversarial Domain Adaptation

  • Apr 09, 2021
  • Weiran Zhang +2
  • Conference Article
  • Citations27

InterBN: Channel Fusion for Adversarial Unsupervised Domain Adaptation

  • Oct 17, 2021
  • Mengzhu Wang +8
  • Research Article
  • Citations31

Robust adversarial discriminative domain adaptation for real-world cross-domain visual recognition

  • Jan 02, 2021
  • Neurocomputing
  • Jianfei Yang +3
  • Research Article
  • Citations20

Adversarial open set domain adaptation via progressive selection of transferable target samples

  • May 30, 2020
  • Neurocomputing
  • Yuan Gao +4
  • Research Article

Improving Unsupervised Domain Adaptation via Multiple Adversarial Learning

  • Oct 01, 2023
  • 電腦學刊
  • Yu-Dong Cao Yu-Dong Cao +2
  • Research Article
  • Citations2

Towards Discriminative Class-Aware Domain Alignment via Coding Rate Reduction for Unsupervised Adversarial Domain Adaptation

  • Sep 16, 2024
  • Symmetry
  • Jiahua Wu +1
  • Research Article
  • Citations15

Unsupervised Multitarget Domain Adaptation With Dictionary-Bridged Knowledge Exploitation.

  • Mar 01, 2024
  • IEEE Transactions on Neural Networks and Learning Systems
  • Qing Tian +5
  • Research Article

Dual pseudo-labeling based adversarial domain adaptation for EEG-based emotion recognition

  • Jan 29, 2026
  • Biomedical Physics & Engineering Express
  • Ling Huang +3
  • Research Article
  • Citations15

Domain Prompt Tuning via Meta Relabeling for Unsupervised Adversarial Adaptation

  • Jan 01, 2024
  • IEEE Transactions on Multimedia
  • Xin Jin +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.