NDLI: High-dimensional signature compression for large-scale image classification

Content Provider	IEEE Xplore Digital Library
Author	Sanchez, J. Perronnin, F.
Copyright Year	2011
Description	Author affiliation: Textual and Visual Pattern Analysis (TVPA) group, Xerox Research Centre Europe (XRCE) (Sanchez, J.; Perronnin, F.)
Abstract	We address image classification on a large-scale, i.e. when a large number of images and classes are involved. First, we study classification accuracy as a function of the image signature dimensionality and the training set size. We show experimentally that the larger the training set, the higher the impact of the dimensionality on the accuracy. In other words, high-dimensional signatures are important to obtain state-of-the-art results on large datasets. Second, we tackle the problem of data compression on very large signatures (on the order of $10^{5}$ dimensions) using two lossy compression strategies: a dimensionality reduction technique known as the hash kernel and an encoding technique based on product quantizers. We explain how the gain in storage can be traded against a loss in accuracy and/or an increase in CPU cost. We report results on two large databases — ImageNet and a dataset of lM Flickr images — showing that we can reduce the storage of our signatures by a factor 64 to 128 with little loss in accuracy. Integrating the decompression in the classifier learning yields an efficient and scalable training algorithm. On ILSVRC2010 we report a 74.3% accuracy at top-5, which corresponds to a 2.5% absolute improvement with respect to the state-of-the-art. On a subset of 10K classes of ImageNet we report a top-1 accuracy of 16.7%, a relative improvement of 160% with respect to the state-of-the-art.
Starting Page	1665
Ending Page	1672
File Size	200896
Page Count	8
File Format	PDF
ISBN	9781457703942
ISSN	10636919
e-ISBN	9781457703959
DOI	10.1109/CVPR.2011.5995504
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2011-06-20
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Accuracy Training Image coding Encoding Kernel Data compression Vectors
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

Local Hybrid Coding for Image Classification

Large-scale image classification: Fast feature extraction and SVM training

Large-scale image classification using supervised spatial encoder

Supervised Kernel Descriptors for Visual Recognition

Sparse Output Coding for Large-Scale Visual Recognition

Efficient Feature Extraction, Encoding, and Classification for Action Recognition

Multi-layer group sparse coding — For concurrent image classification and annotation

Meta-class features for large-scale object categorization on a budget

Beyond spatial pyramids: Receptive field learning for pooled image features

High-dimensional signature compression for large-scale image classification

Similar Documents

Local Hybrid Coding for Image Classification

Large-scale image classification: Fast feature extraction and SVM training

Large-scale image classification using supervised spatial encoder

Supervised Kernel Descriptors for Visual Recognition

Sparse Output Coding for Large-Scale Visual Recognition

Efficient Feature Extraction, Encoding, and Classification for Action Recognition

Multi-layer group sparse coding — For concurrent image classification and annotation

Meta-class features for large-scale object categorization on a budget

Beyond spatial pyramids: Receptive field learning for pooled image features

High-dimensional signature compression for large-scale image classification