• Home
  • Search
  • Domain Generalization and Adaptation Using Low Rank Exemplar SVMs.
  • Cite Icon166
  • https://doi.org/10.1109/tpami.2017.2704624Copy DOI Icon

Domain Generalization and Adaptation Using Low Rank Exemplar SVMs.

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

Domain adaptation between diverse source and target domains is challenging, especially in the real-world visual recognition tasks where the images and videos consist of significant variations in viewpoints, illuminations, qualities, etc. In this paper, we propose a new approach for domain generalization and domain adaptation based on exemplar SVMs. Specifically, we decompose the source domain into many subdomains, each of which contains only one positive training sample and all negative samples. Each subdomain is relatively less diverse, and is expected to have a simpler distribution. By training one exemplar SVM for each subdomain, we obtain a set of exemplar SVMs. To further exploit the inherent structure of source domain, we introduce a nuclear-norm based regularizer into the objective function in order to enforce the exemplar SVMs to produce a low-rank output on training samples. In the prediction process, the confident exemplar SVM classifiers are selected and reweigted according to the distribution mismatch between each subdomain and the test sample in the target domain. We formulate our approach based on the logistic regression and least square SVM algorithms, which are referred to as low rank exemplar SVMs (LRE-SVMs) and low rank exemplar least square SVMs (LRE-LSSVMs), respectively. A fast algorithm is also developed for accelerating the training of LRE-LSSVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation, and show that our approach can also be applied to domain adaptation with evolving target domain, where the target data distribution is gradually changing. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation with fixed and evolving target domains.

Similar Papers
  • Conference Article
  • Citations82

Multi-view Domain Generalization for Visual Recognition

  • Dec 01, 2015
  • Li Niu +2
  • Research Article
  • Citations60

Domain Adaptation for Remote Sensing Image Semantic Segmentation: An Integrated Approach of Contrastive Learning and Adversarial Learning

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Lubin Bai +5
  • Research Article
  • Citations6

Label Space Embedding of Manifold Alignment for Domain Adaption

  • Mar 21, 2018
  • Neural Processing Letters
  • Jing Wang +2
  • Research Article
  • Citations6

Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation

  • Mar 04, 2022
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jinfeng Li +5
  • Research Article
  • Citations18

Attention Cycle-consistent universal network for More Universal Domain Adaptation

  • Nov 08, 2023
  • Pattern Recognition
  • Ziyun Cai +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
  • Citations3

Latent space search approach for domain adaptation

  • Mar 21, 2024
  • Expert Systems with Applications
  • Mingjie Gao +1
  • 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
  • Research Article
  • Citations108

Domain Adaptation for Face Recognition: Targetize Source Domain Bridged by Common Subspace

  • Dec 31, 2013
  • International Journal of Computer Vision
  • Meina Kan +3
  • Research Article
  • Citations16

BAN: A Universal Paradigm for Cross-Scene Classification Under Noisy Annotations From RGB and Hyperspectral Remote Sensing Images

  • Jan 01, 2025
  • IEEE Transactions on Geoscience and Remote Sensing
  • Wentang Chen +4
  • Conference Article
  • Citations14

Three viewpoints toward exemplar SVM

  • Jun 01, 2015
  • Takumi Kobayashi
  • Conference Article

Joint Distribution Adaptation via Wasserstein Adversarial Training

  • Jul 18, 2021
  • Xiaolu Wang +3
  • Conference Article
  • Citations6

Discovering Domain Disentanglement for Generalized Multi-Source Domain Adaptation

  • Jul 18, 2022
  • Zixin Wang +4
  • Book Chapter
  • Citations19

Dictionary-Based Domain Adaptation Methods for the Re-identification of Faces

  • Jan 01, 2014
  • Qiang Qiu +2
  • Conference Article
  • Citations4

Machine Learning Pipeline for Reusing Pretrained Models

  • Nov 02, 2020
  • Maryam Alshehhi +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.