• Home
  • Search
  • A Feature Selection Approach to Visual Domain Adaptation in Classification
  • Cite Icon7
  • https://doi.org/10.1007/978-3-030-63833-7_7Copy DOI Icon

A Feature Selection Approach to Visual Domain Adaptation in Classification

  • Jan 1, 2020
  • Rakesh Kumar Sanodiya +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In machine learning, we presume datasets to be labeled while performing any operation. But, is it true in real-life scenarios? To its contrary, we have an enormous amount of unlabeled datasets available in the form of images, videos, audios, articles, and many more. The major challenge we face is to train our classification model with primitive machine learning algorithms because these algorithms only expect labeled data. To overcome these limitations visual domain adaptation algorithms such as MEDA (Manifold Embedded Distribution Alignment) have been introduced. The main motto of MEDA is to minimize the distribution difference between the source domain (an application that contains enough labeled data) and the target domain (an application that contains only unlabeled data). In this way, the source domain labeled data can be utilized to enhance the performance of the target domain classifier. Though MEDA (Manifold Embedded Distribution Alignment) approach shows remarkable improvement in classification accuracy, but still there is considerable scope of improvement. There are plenty of irrelevant features in both domains. These irrelevant features create a hole for this algorithm and prevent the target domain classifier from becoming more robust. Therefore, for the purpose of filling this hole, we propose a new feature selection based visual domain adaptation (FSVDA) method which uses particle swarm optimization (PSO), where the MEDA method is considered as a fitness function that leads to automatically select a good subset of features over both the domains. Extensive experimental results on two real-world domain adaptation (DA) data sets such as object recognition and digit recognition demonstrate that our proposed method outperforms state-of-the-art primitive and domain DA algorithms. It is a big challenge to train the classifier for a new unlabeled image dataset in image classification and computer vision. The two magnificent solutions to this challenge are transfer learning and domain adaptation. By transfer learning, we can use our knowledge from previously trained models for training newer models.

Similar Papers
  • Research Article
  • Citations11

A Probabilistic Covariate Shift Assumption for Domain Adaptation

  • Feb 21, 2015
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Tameem Adel +1
  • Conference Article
  • Citations5

Statistical and Geometrical Alignment using Metric Learning in Domain Adaptation

  • Jul 01, 2020
  • Rakesh Kumar Sanodiya +3
  • Conference Article
  • Citations2

Multi-source based approach for Visual Domain Adaptation

  • Jul 18, 2021
  • Mrinalini Tiwari +3
  • Research Article
  • Citations10

Iterative joint classifier and domain adaptation for visual transfer learning

  • Sep 29, 2021
  • International Journal of Machine Learning and Cybernetics
  • Shiva Noori Saray +1
  • Dissertation

Towards robust sensing and recognition : from statistical learning to transfer learning

  • Jan 01, 2020
  • Jianfei Yang
  • Conference Article
  • Citations734

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

  • Oct 15, 2018
  • Jindong Wang +5
  • Conference Article
  • Citations364

Robust visual domain adaptation with low-rank reconstruction

  • Jun 01, 2012
  • I-Hong Jhuo +3
  • Conference Article
  • Citations4

Machine Learning Pipeline for Reusing Pretrained Models

  • Nov 02, 2020
  • Maryam Alshehhi +1
  • Dissertation

Learning Invariances for High-Dimensional Data Analysis

  • Jan 01, 2014
  • The University of Queensland
  • Mahsa Baktashmotlagh
  • Conference Article
  • Citations4

Domain-Adaptive TinyML Model for Efficient Pest and Disease Detection in Domestic Crops: A Practical Approach for Developing Countries

  • Sep 04, 2024
  • Gibson Kimutai +1
  • Book Chapter
  • Citations2

Unified Framework for Visual Domain Adaptation Using Globality-Locality Preserving Projections

  • Jan 01, 2019
  • Rakesh Kumar Sanodiya +2
  • Research Article
  • Citations11

Multi-Source Selection Transfer Learning with Privacy-Preserving

  • May 07, 2022
  • Neural Processing Letters
  • Weifei Wu
  • Conference Article
  • Citations46

Adversarial Bipartite Graph Learning for Video Domain Adaptation

  • Oct 12, 2020
  • Yadan Luo +4
  • Conference Article
  • Citations4

A Feature and Parameter Selection Approach for Visual Domain Adaptation using Particle Swarm Optimization

  • Jul 18, 2022
  • Ravi Ranjan Prasad Karn +6
  • Conference Article
  • Citations4

CAFT: Class Aware Frequency Transform for Reducing Domain Gap

  • Oct 01, 2021
  • Vikash Kumar +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.