NDLI: Filter Forests for Learning Data-Dependent Convolutional Kernels

Content Provider	IEEE Xplore Digital Library
Author	Fanello, S.R. Keskin, C. Kohli, P. Izadi, S. Shotton, J. Criminisi, A. Pattacini, U. Paek, T.
Copyright Year	2014
Abstract	We propose 'filter forests' (FF), an efficient new discriminative approach for predicting continuous variables given a signal and its context. FF can be used for general signal restoration tasks that can be tackled via convolutional filtering, where it attempts to learn the optimal filtering kernels to be applied to each data point. The model can learn both the size of the kernel and its values, conditioned on the observation and its spatial or temporal context. We show that FF compares favorably to both Markov random field based and recently proposed regression forest based approaches for labeling problems in terms of efficiency and accuracy. In particular, we demonstrate how FF can be used to learn optimal denoising filters for natural images as well as for other tasks such as depth image refinement, and 1D signal magnitude estimation. Numerous experiments and quantitative comparisons show that FFs achieve accuracy at par or superior to recent state of the art techniques, while being several orders of magnitude faster.
Starting Page	1709
Ending Page	1716
File Size	2172276
Page Count	8
File Format	PDF
ISBN	9781479951185
ISSN	10636919
DOI	10.1109/CVPR.2014.221
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	Kernel Training Convolution Noise measurement Noise Vegetation Principal component analysis Statistical Methods Decision Trees Image Denoising Image Enhancement Image Restoration
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

Context-Dependent Kernels for Object Classification

Structured Forests for Fast Edge Detection

Image deblurring and denoising using color priors

Revisiting Example Dependent Cost-Sensitive Learning with Decision Trees

On learning optimized reaction diffusion processes for effective image restoration

Alternating Decision Forests

PReLU and edge-aware filter-based image denoiser using convolutional neural network

Structured class-labels in random forests for semantic image labelling

Fully synthetic training for image restoration tasks

Filter Forests for Learning Data-Dependent Convolutional Kernels

Similar Documents

Context-Dependent Kernels for Object Classification

Structured Forests for Fast Edge Detection

Image deblurring and denoising using color priors

Revisiting Example Dependent Cost-Sensitive Learning with Decision Trees

On learning optimized reaction diffusion processes for effective image restoration

Alternating Decision Forests

PReLU and edge-aware filter-based image denoiser using convolutional neural network

Structured class-labels in random forests for semantic image labelling

Fully synthetic training for image restoration tasks

Filter Forests for Learning Data-Dependent Convolutional Kernels