• Home
  • Search
  • Partial Domain Adaptation Without Domain Alignment.
  • Open Access IconOpen Access
  • Cite Icon30
  • https://doi.org/10.1109/tpami.2022.3228937Copy DOI Icon

Partial Domain Adaptation Without Domain Alignment.

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

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a well-labeled source domain to a related and unlabeled target domain with identical label space. The main workhorse in UDA is domain alignment and has proven successful. However, it is practically difficult to find an appropriate source domain with identical label space. A more practical scenario is partial domain adaptation (PDA) where the source label space subsumes the target one. Unfortunately, due to the non-identity between label spaces, it is extremely hard to obtain an ideal alignment, conversely, easier resulting in mode collapse and negative transfer. These motivate us to find a relatively simpler alternative to solve PDA. To achieve this, we first explore a theoretical analysis, which says that the target risk is bounded by both model smoothness and between-domain discrepancy. Then, we instantiate the model smoothness as an intra-domain structure preserving (IDSP) while giving up possibly riskier domain alignment. To our best knowledge, this is the first naive attempt for PDA without alignment. Finally, our empirical results on benchmarks demonstrate that IDSP is not only superior to the PDA SOTAs (e.g., ∼+10% on Cl → Rw and ∼+8% on Ar → Rw), but also complementary to domain alignment in the standard UDA.

Similar Papers
  • Research Article

Tight Source Domain Match for Partial Domain Adaptation Based on Maximum Density

  • May 01, 2022
  • Journal of Physics Conference Series
  • Zi-Ao Ni +4
  • Research Article
  • Citations15

Manifold discrimination partial adversarial domain adaptation

  • Jun 25, 2022
  • Knowledge-Based Systems
  • Chunmei He +4
  • Book Chapter
  • Citations541

Partial Adversarial Domain Adaptation

  • Jan 01, 2018
  • Zhangjie Cao +3
  • Research Article
  • Citations31

Improving the Transferability of Deep Learning Models for Crop Yield Prediction: A Partial Domain Adaptation Approach

  • Sep 16, 2023
  • Remote Sensing
  • Yuchi Ma +3
  • Research Article
  • Citations43

Learning Target-Domain-Specific Classifier for Partial Domain Adaptation.

  • May 01, 2021
  • IEEE Transactions on Neural Networks and Learning Systems
  • Chuan-Xian Ren +3
  • Research Article
  • Citations99

A Stacked Auto-Encoder Based Partial Adversarial Domain Adaptation Model for Intelligent Fault Diagnosis of Rotating Machines

  • Dec 15, 2020
  • IEEE Transactions on Industrial Informatics
  • Zhao-Hua Liu +5
  • Dissertation

Robust and efficient deep learning methods for vision-based action recognition

  • Jan 01, 2021
  • Yuecong Xu
  • Research Article
  • Citations24

Partial adversarial domain adaptation by dual-domain alignment for fault diagnosis of rotating machines

  • Nov 28, 2022
  • ISA Transactions
  • Xuan Wang +4
  • Conference Article
  • Citations26

Partial Video Domain Adaptation with Partial Adversarial Temporal Attentive Network

  • Oct 01, 2021
  • Yuecong Xu +5
  • Research Article
  • Citations6

Partial domain adaptation based on shared class oriented adversarial network

  • Jun 20, 2020
  • Computer Vision and Image Understanding
  • Wenjie Qiu +2
  • Conference Article
  • Citations2

CANN

  • Oct 26, 2021
  • Cheng Feng +4
  • Book Chapter
  • Citations9

Adversarial Partial Domain Adaptation by Cycle Inconsistency

  • Jan 01, 2022
  • Kun-Yu Lin +3
  • Book Chapter
  • Citations28

Discriminative Partial Domain Adversarial Network

  • Jan 01, 2020
  • Jian Hu +7
  • Research Article
  • Citations178

Deep Residual Correction Network for Partial Domain Adaptation.

  • Jan 07, 2020
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Shuang Li +6
  • Research Article
  • Citations49

Unsupervised Domain Adaptation via Importance Sampling

  • Jan 03, 2020
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Xuemiao Xu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.