NDLI: Leveraging category-level labels for instance-level image retrieval

Content Provider	IEEE Xplore Digital Library
Author	Gordoa, A. Rodriguez-Serrano, J.A. Perronnin, F. Valveny, E.
Copyright Year	2012
Description	Author affiliation: Textual and Visual Pattern Analysis, Xerox Research Center Europe, France (Gordoa, A.; Rodriguez-Serrano, J.A.; Perronnin, F.) \|\| Computer Vision Center, Universität Autònoma de Barcelona, Spain (Valveny, E.)
Abstract	In this article, we focus on the problem of large-scale instance-level image retrieval. For efficiency reasons, it is common to represent an image by a fixed-length descriptor which is subsequently encoded into a small number of bits. We note that most encoding techniques include an unsupervised dimensionality reduction step. Our goal in this work is to learn a better subspace in a supervised manner. We especially raise the following question: "can category-level labels be used to learn such a subspace?" To answer this question, we experiment with four learning techniques: the first one is based on a metric learning framework, the second one on attribute representations, the third one on Canonical Correlation Analysis (CCA) and the fourth one on Joint Subspace and Classifier Learning (JSCL). While the first three approaches have been applied in the past to the image retrieval problem, we believe we are the first to show the usefulness of JSCL in this context. In our experiments, we use ImageNet as a source of category-level labels and report retrieval results on two standard dataseis: INRIA Holidays and the University of Kentucky benchmark. Our experimental study shows that metric learning and attributes do not lead to any significant improvement in retrieval accuracy, as opposed to CCA and JSCL. As an example, we report on Holidays an increase in accuracy from 39.3% to 48.6% with 32-dimensional representations. Overall JSCL is shown to yield the best results.
Starting Page	3045
Ending Page	3052
File Size	293579
Page Count	8
File Format	PDF
ISBN	9781467312264
ISSN	10636919
e-ISBN	9781467312288
e-ISBN	9781467312271
DOI	10.1109/CVPR.2012.6248035
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2012-06-16
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Measurement Vectors Principal component analysis Accuracy Encoding Correlation Image retrieval
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Discriminative high order SVD: Adaptive tensor subspace selection for image classification, clustering, and retrieval

Towards Good Practices for Action Video Encoding

Combining attributes and Fisher vectors for efficient image retrieval

Learning component-level sparse representation using histogram information for image classification

Learning Semantic Binary Codes by Encoding Attributes for Image Retrieval

Scene classification with semantic Fisher vectors

A-Optimal Non-negative Projection for image representation

Event Retrieval in Large Video Collections with Circulant Temporal Encoding

Face image retrieval by shape manipulation

Leveraging category-level labels for instance-level image retrieval

Similar Documents

Discriminative high order SVD: Adaptive tensor subspace selection for image classification, clustering, and retrieval

Towards Good Practices for Action Video Encoding

Combining attributes and Fisher vectors for efficient image retrieval

Learning component-level sparse representation using histogram information for image classification

Learning Semantic Binary Codes by Encoding Attributes for Image Retrieval

Scene classification with semantic Fisher vectors

A-Optimal Non-negative Projection for image representation

Event Retrieval in Large Video Collections with Circulant Temporal Encoding

Face image retrieval by shape manipulation

Leveraging category-level labels for instance-level image retrieval