Domain adaptive Fisher vector for visual recognition

Li Niu, Jianfei Cai, Dong Xu

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

7 Citations (Scopus)


In this paper, we consider Fisher vector in the context of domain adaptation, which has rarely been discussed by the existing domain adaptation methods. Particularly, in many real scenarios, the distributions of Fisher vectors of the training samples (i.e., source domain) and test samples (i.e., target domain) are considerably different, which may degrade the classification performance on the target domain by using the classifiers/regressors learnt based on the training samples from the source domain. To address the domain shift issue, we propose a Domain Adaptive Fisher Vector (DAFV) method, which learns a transformation matrix to select the domain invariant components of Fisher vectors and simultaneously solves a regression problem for visual recognition tasks based on the transformed features. Specifically, we employ a group lasso based regularizer on the transformation matrix to select the components of Fisher vectors, and use a regularizer based on the Maximum Mean Discrepancy (MMD) criterion to reduce the data distribution mismatch of transformed features between the source domain and the target domain. Comprehensive experiments demonstrate the effectiveness of our DAFV method on two benchmark datasets.

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2016
Subtitle of host publication14th European Conference Amsterdam, The Netherlands, October 11–14, 2016 Proceedings, Part VI
EditorsBastian Leibe, Jiri Matas, Nicu Sebe, Max Welling
Place of PublicationCham Switzerland
Number of pages17
ISBN (Electronic)9783319464664
ISBN (Print)9783319464657
Publication statusPublished - 2016
Externally publishedYes
EventEuropean Conference on Computer Vision 2016 - Amsterdam, Netherlands
Duration: 11 Oct 201614 Oct 2016
Conference number: 14th (Proceedings)

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceEuropean Conference on Computer Vision 2016
Abbreviated titleECCV 2016
Internet address


  • Domain adaptation
  • Fisher vector

Cite this