• Home
  • Search
  • Unsupervised Adaptation Across Domain Shifts by Generating Intermediate Data Representations
  • Cite Icon257
  • https://doi.org/10.1109/tpami.2013.249Copy DOI Icon

Unsupervised Adaptation Across Domain Shifts by Generating Intermediate Data Representations

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

With unconstrained data acquisition scenarios widely prevalent, the ability to handle changes in data distribution across training and testing data sets becomes important. One way to approach this problem is through domain adaptation, and in this paper we primarily focus on the unsupervised scenario where the labeled source domain training data is accompanied by unlabeled target domain test data. We present a two-stage data-driven approach by generating intermediate data representations that could provide relevant information on the domain shift. Starting with a linear representation of domains in the form of generative subspaces of same dimensions for the source and target domains, we first utilize the underlying geometry of the space of these subspaces, the Grassmann manifold, to obtain a `shortest' geodesic path between the two domains. We then sample points along the geodesic to obtain intermediate cross-domain data representations, using which a discriminative classifier is learnt to estimate the labels of the target data. We subsequently incorporate non-linear representation of domains by considering a Reproducing Kernel Hilbert Space representation, and a low-dimensional manifold representation using Laplacian Eigenmaps, and also examine other domain adaptation settings such as (i) semi-supervised adaptation where the target domain is partially labeled, and (ii) multi-domain adaptation where there could be more than one domain in source and/or target data sets. Finally, we supplement our adaptation technique with (i) fine-grained reference domains that are created by blending samples from source and target data sets to provide some evidence on the actual domain shift, and (ii) a multi-class boosting analysis to obtain robustness to the choice of algorithm parameters. We evaluate our approach for object recognition problems and report competitive results on two widely used Office and Bing adaptation data sets.

Similar Papers
  • Research Article
  • Citations35

Domain Adaptation for Visual Recognition

  • Mar 11, 2015
  • Foundations and Trends® in Computer Graphics and Vision
  • Raghuraman Gopalan +3
  • Research Article
  • Citations1

IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation

  • Apr 28, 2025
  • ACM Transactions on Intelligent Systems and Technology
  • Shima Rashidi +9
  • Conference Article
  • Citations3

SLA+: Narrowing the Difference between Data Sets in Heterogenous Cross-Project Defection Prediction

  • Jul 01, 2020
  • Jie Wu +3
  • Research Article
  • Citations15

DualDA-Net: Dual-Head Rectification for Cross-Domain Object Detection of Remote Sensing

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yangguang Zhu +4
  • Conference Article
  • Citations43

Leaf Counting Without Annotations Using Adversarial Unsupervised Domain Adaptation

  • Jun 01, 2019
  • Mario Valerio Giuffrida +3
  • Research Article
  • Citations26

Knowledge distillation methods for efficient unsupervised adaptation across multiple domains

  • Jan 06, 2021
  • Image and Vision Computing
  • Le Thanh Nguyen-Meidine +5
  • Conference Article
  • Citations77

Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder

  • Oct 01, 2021
  • Hanwen Liang +3
  • Research Article
  • Citations20

A Transfer Reinforcement Learning Framework for Smart Home Energy Management Systems

  • Feb 15, 2023
  • IEEE Sensors Journal
  • Murad Khan +4
  • PDF
  • Research Article
  • Citations8

Multiple-level biomedical event trigger recognition with transfer learning

  • Sep 06, 2019
  • BMC Bioinformatics
  • Yifei Chen
  • Research Article
  • Citations32

Assessing fusarium oxysporum disease severity in cotton using unmanned aerial system images and a hybrid domain adaptation deep learning time series model

  • Jan 01, 2024
  • Biosystems Engineering
  • Alwaseela Abdalla +5
  • Conference Article
  • Citations18

Domain adaptation for retinal vessel segmentation using asymmetrical maximum classifier discrepancy

  • May 17, 2019
  • Jingyu Zhuang +4
  • Conference Article
  • Citations4

Machine Learning Pipeline for Reusing Pretrained Models

  • Nov 02, 2020
  • Maryam Alshehhi +1
  • Conference Article
  • Citations3

A novel H and E color augmentation for domain invariance classification of unannotated histopathology prostate cancer images

  • Apr 07, 2023
  • Roozbeh Bazargani +7
  • PDF
  • Research Article
  • Citations5

Semi-Supervised Domain Adaptation for Holistic Counting under Label Gap

  • Sep 29, 2021
  • Journal of Imaging
  • Mattia Litrico +3
  • Research Article
  • Citations15

Easy-to-Hard Structure for Remote Sensing Scene Classification in Multitarget Domain Adaptation

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Ba Hung Ngo +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.