• Home
  • Search
  • Learning Across Tasks for Zero-Shot Domain Adaptation From a Single Source Domain.
  • Cite Icon31
  • https://doi.org/10.1109/tpami.2021.3088859Copy DOI Icon

Learning Across Tasks for Zero-Shot Domain Adaptation From a Single Source Domain.

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

Domain adaptation techniques learn transferable knowledge from a source domain to a target domain and train models that generalize well in the target domain. Unfortunately, a majority of the existing techniques are only applicable to scenarios that the target-domain data in the task of interest is available for training, yet this is not often true in practice. In general, human beings are experts in generalization across domains. For example, a baby can easily identify the bear from a clipart image after learning this category of animal from the photo images. To reduce the gap between the generalization ability of human and that of machines, we propose a new solution to the challenging zero-shot domain adaptation (ZSDA) problem, where only a single source domain is available and the target domain for the task of interest is not accessible. Inspired by the observation that the knowledge about domain correlation can improve our generalization ability, we explore the correlation between source domain and target domain in an irrelevant knowledge task ([Formula: see text]-task), where dual-domain samples are available. We denote the task of interest as the question task ([Formula: see text]-task) and synthesize its non-accessible target-domain as such that these two tasks have the shared domain correlation. In order to realize our idea, we introduce a new network structure, i.e., conditional coupled generative adversarial networks (CoCoGAN), by extending the coupled generative adversarial networks (CoGAN) into a conditioning model. With a pair of coupling GANs, our CoCoGAN is able to capture the joint distribution of data samples across two domains and two tasks. For CoCoGAN training in a ZSDA task, we introduce three supervisory signals, i.e., semantic relationship consistency across domains, global representation alignment across tasks, and alignment consistency across domains. Experimental results demonstrate that our method can learn a suitable model for the non-accessible target domain and outperforms the existing state of the arts in both image classification and semantic segmentation.

Similar Papers
  • Conference Article
  • Citations51

Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation

  • Oct 01, 2019
  • Jinghua Wang +1
  • Research Article
  • Citations31

Domain Shift Preservation for Zero-Shot Domain Adaptation.

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Jinghua Wang +2
  • Conference Article
  • Citations65

StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization

  • Jun 01, 2020
  • Onur Tasar +4
  • Research Article
  • Citations16

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

  • Sep 17, 2024
  • Pattern Recognition
  • Zicheng Pan +3
  • Research Article
  • Citations41

Learning Causal Representations for Robust Domain Adaptation

  • Jan 01, 2021
  • IEEE Transactions on Knowledge and Data Engineering
  • Shuai Yang +5
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Research Article
  • Citations77

Multi-Source Contribution Learning for Domain Adaptation.

  • Oct 01, 2022
  • IEEE Transactions on Neural Networks and Learning Systems
  • Keqiuyin Li +3
  • Conference Article
  • Citations4

Machine Learning Pipeline for Reusing Pretrained Models

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

Domain Adaptation Fault Diagnosis Method Based on Dual-Stage Progressive Alignment

  • Dec 01, 2025
  • Journal of Physics: Conference Series
  • Zhenghong Wu +5
  • 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
  • Citations7

Reversed domain adaptation for nuclei segmentation-based pathological image classification

  • Nov 18, 2023
  • Computers in Biology and Medicine
  • Zhixin Xu +3
  • Research Article
  • Citations1

A multi-source domain adaption intelligent fault diagnosis method based on asymmetric adversarial training

  • Feb 18, 2025
  • Measurement Science and Technology
  • Dan Yang +2
  • Research Article
  • Citations3

An integrating multidimensional features method based on multi-view learning for intelligent fault diagnosis of rolling bearings

  • Apr 18, 2025
  • Engineering Computations
  • Min Wang +5
  • Conference Article
  • Citations3

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

  • Jan 01, 2014
  • Suranjana Samanta +2
  • Book Chapter
  • Citations18

Adversarial Learning for Zero-Shot Domain Adaptation

  • Jan 01, 2020
  • Jinghua Wang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.