NDLI: Generalized Max Pooling

Content Provider	IEEE Xplore Digital Library
Author	Murray, N. Perronnin, F.
Copyright Year	2014
Abstract	State-of-the-art patch-based image representations involve a pooling operation that aggregates statistics computed from local descriptors. Standard pooling operations include sum- and max-pooling. Sum-pooling lacks discriminability because the resulting representation is strongly influenced by frequent yet often uninformative descriptors, but only weakly influenced by rare yet potentially highly-informative ones. Max-pooling equalizes the influence of frequent and rare descriptors but is only applicable to representations that rely on count statistics, such as the bag-of-visual-words (BOV)and its soft- and sparse-coding extensions. We propose a novel pooling mechanism that achieves the same effect as max-pooling but is applicable beyond the BOV and especially to the state-of-the-art Fisher Vector -- hence the name Generalized Max Pooling (GMP). It involves equalizing the similarity between each patch and the pooled representation, which is shown to be equivalent to re-weighting the per-patch statistics. We show on five public image classification benchmarks that the proposed GMP can lead to significant performance gains with respect to heuristic alternatives.
Starting Page	2473
Ending Page	2480
File Size	459626
Page Count	8
File Format	PDF
ISBN	9781479951185
ISSN	10636919
DOI	10.1109/CVPR.2014.317
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-06-23
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Encoding Birds Vectors Visualization Computer vision Standards Kernel classification pooling image representations
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

Geometric ℓp-norm feature pooling for image classification

Hierarchical matching with side information for image classification

Ask the Image: Supervised Pooling to Preserve Feature Locality

Pose pooling kernels for sub-category recognition

Supervised Kernel Descriptors for Visual Recognition

Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition

High-dimensional signature compression for large-scale image classification

Scene classification with semantic Fisher vectors

Sparse representations of clustered video shots for action recognition

Generalized Max Pooling

Similar Documents

Geometric ℓp-norm feature pooling for image classification

Hierarchical matching with side information for image classification

Ask the Image: Supervised Pooling to Preserve Feature Locality

Pose pooling kernels for sub-category recognition

Supervised Kernel Descriptors for Visual Recognition

Hierarchical Joint Max-Margin Learning of Mid and Top Level Representations for Visual Recognition

High-dimensional signature compression for large-scale image classification

Scene classification with semantic Fisher vectors

Sparse representations of clustered video shots for action recognition

Generalized Max Pooling