NDLI: Beyond spatial pyramids: Receptive field learning for pooled image features

Content Provider	IEEE Xplore Digital Library
Author	Yangqing Jia Chang Huang Darrell, T.
Copyright Year	2012
Description	Author affiliation: UC Berkeley EECS & ICSI (Yangqing Jia; Darrell, T.) \|\| NEC Labs America (Chang Huang)
Abstract	In this paper we examine the effect of receptive field designs on classification accuracy in the commonly adopted pipeline of image classification. While existing algorithms usually use manually defined spatial regions for pooling, we show that learning more adaptive receptive fields increases performance even with a significantly smaller codebook size at the coding layer. To learn the optimal pooling parameters, we adopt the idea of over-completeness by starting with a large number of receptive field candidates, and train a classifier with structured sparsity to only use a sparse subset of all the features. An efficient algorithm based on incremental feature selection and retraining is proposed for fast learning. With this method, we achieve the best published performance on the CIFAR-10 dataset, using a much lower dimensional feature space than previous methods.
Starting Page	3370
Ending Page	3377
File Size	735761
Page Count	8
File Format	PDF
ISBN	9781467312264
ISSN	10636919
e-ISBN	9781467312288
e-ISBN	9781467312271
DOI	10.1109/CVPR.2012.6248076
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	Encoding Dictionaries Pipelines Image coding Vectors Accuracy Training data
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

Supervised Kernel Descriptors for Visual Recognition

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

Latent Dictionary Learning for Sparse Representation Based Classification

High-dimensional signature compression for large-scale image classification

Ask the locals: Multi-way local pooling for image recognition

Transfer Sparse Coding for Robust Image Representation

Fisher Discrimination Dictionary Learning for sparse representation

Relaxed collaborative representation for pattern classification

Beyond spatial pyramids: Receptive field learning for pooled image features

Similar Documents

Local Hybrid Coding for Image Classification

Supervised Kernel Descriptors for Visual Recognition

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

Latent Dictionary Learning for Sparse Representation Based Classification

High-dimensional signature compression for large-scale image classification

Ask the locals: Multi-way local pooling for image recognition

Transfer Sparse Coding for Robust Image Representation

Fisher Discrimination Dictionary Learning for sparse representation

Relaxed collaborative representation for pattern classification

Beyond spatial pyramids: Receptive field learning for pooled image features