• Home
  • Search
  • Statistical and Geometrical Alignment for Unsupervised Deep Domain Adaptation
  • https://doi.org/10.1007/978-981-33-4087-9_37Copy DOI Icon

Statistical and Geometrical Alignment for Unsupervised Deep Domain Adaptation

  • Jan 1, 2021
  • Leehter Yao +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

The concept of domain adaptation (DA) is based on the principle of information transfer from one domain (usually called source domain) to a different but related other domain (usually called target domain). The past few years have seen a considerable inclination towards the development of deep-domain adaptation approaches. The majority of the existing approaches minimize distribution divergence between both domains to learn shared feature space. One of the shortcomings of existing domain alignment methods is their inability to preserve the original similarity of the data samples in the learned hyperplane. Due to which, data samples far from their respective class distribution or near the edge of it can be incorrectly classified in the hyperplane learned from both domain data distribution. In this work, we propose a novel deep learning approach called Statistical and Geometric Alignment for Unsupervised Deep Domain Adaptation (SGA-UDDA) that minimizes the geometric and statistical shifts between both domains and makes the target domain classifier more robust. A substantial amount of experiments have validated that our proposed SGA-UDDA algorithm surpasses many advanced deep-domain adaptations and statistical domain adaptation methods when the tests were conducted on real-world data-sets.

Similar Papers
  • Conference Article
  • Citations10

Class Consistency Driven Unsupervised Deep Adversarial Domain Adaptation

  • Jun 01, 2019
  • Sayan Rakshit +3
  • Research Article
  • Citations21

Deep domain adaptation with ordinal regression for pain assessment using weakly-labeled videos

  • Apr 08, 2021
  • Image and Vision Computing
  • Gnana Praveen Rajasekhar +2
  • Research Article
  • Citations6

Transfer learning with unsupervised domain adaptation for personal thermal comfort prediction

  • Apr 01, 2025
  • Energy and Buildings
  • Chuangkang Yang +2
  • 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
  • Book Chapter
  • Citations8

Domain Adaptation for Eye Segmentation

  • Jan 01, 2020
  • Yiru Shen +2
  • Research Article
  • Citations19

Pseudo-Label-Assisted Subdomain Adaptation for Hyperspectral Image Classification

  • Jun 01, 2024
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Zhixi Feng +4
  • Research Article
  • Citations25

Domain consistency regularization for unsupervised multi-source domain adaptive classification

  • Aug 03, 2022
  • Pattern Recognition
  • Zhipeng Luo +3
  • Research Article
  • Citations2337

Deep visual domain adaptation: A survey

  • May 30, 2018
  • Neurocomputing
  • Mei Wang +1
  • 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

Deep Unsupervised Domain Adaptation for Translating Cancer Dependency Maps From Cell Lines to Breast Cancer Tumor Genomics.

  • Jul 01, 2026
  • Genetic epidemiology
  • Yu Shi +2
  • Research Article
  • Citations5

A Multi-Source Domain Adaptation Method for Bearing Fault Diagnosis with Dynamically Similarity Guidance on Incomplete Data

  • Jan 12, 2025
  • Actuators
  • Juan Tian +3
  • Research Article
  • Citations15

Unsupervised domain adaptation without source data for estimating occupancy and recognizing activities in smart buildings

  • Dec 01, 2023
  • Energy and Buildings
  • Jawher Dridi +2
  • Conference Article
  • Citations94

Multi-Target Domain Adaptation with Collaborative Consistency Learning

  • Jun 01, 2021
  • Takashi Isobe +7
  • Research Article
  • Citations8

Discriminative information preservation: A general framework for unsupervised visual Domain Adaptation

  • May 20, 2021
  • Knowledge-Based Systems
  • Rakesh Kumar Sanodiya +1
  • Conference Article
  • Citations80

Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation

  • Jan 01, 2021
  • L.T Nguyen-Meidine +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.