skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Learning Hierarchical Features for Scene Labeling

IEEE transactions on pattern analysis and machine intelligence, 2013-08, Vol.35 (8), p.1915-1929 [Peer Reviewed Journal]

Distributed under a Creative Commons Attribution 4.0 International License ;ISSN: 0162-8828 ;EISSN: 1939-3539 ;DOI: 10.1109/TPAMI.2012.231

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Learning Hierarchical Features for Scene Labeling
  • Author: Farabet, Clément ; Couprie, Camille ; Najman, Laurent ; Lecun, Yann
  • Subjects: Computer Science ; Computer Vision and Pattern Recognition
  • Is Part Of: IEEE transactions on pattern analysis and machine intelligence, 2013-08, Vol.35 (8), p.1915-1929
  • Description: Scene labeling consists in labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel. The method alleviates the need for engineered features, and produces a powerful representation that captures texture, shape and contextual information. We report results using multiple post-processing methods to produce the final labeling. Among those, we propose a technique to automatically retrieve, from a pool of segmentation components, an optimal set of components that best explain the scene; these components are arbitrary, e.g. they can be taken from a segmentation tree, or from any family of over-segmentations. The system yields record accuracies on the Sift Flow Dataset (33 classes) and the Barcelona Dataset (170 classes) and near-record accuracy on Stanford Background Dataset (8 classes), while being an order of magnitude faster than competing approaches, producing a 320 × 240 image labeling in less than a second, including feature extraction.
  • Publisher: Institute of Electrical and Electronics Engineers
  • Language: English
  • Identifier: ISSN: 0162-8828
    EISSN: 1939-3539
    DOI: 10.1109/TPAMI.2012.231
  • Source: Hyper Article en Ligne (HAL) (Open Access)
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait