Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation

In this paper, we present a large-scale sparse learning (LSSL) approach to solve the challenging task of semantic segmentation of images with noisy tags. Different from the traditional strongly supervised methods that exploit pixel-level labels for semantic segmentation, we make use of much weaker s...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2018-01, Vol.48 (1), p.253-263
Main Authors: Li, Aoxue, Lu, Zhiwu, Wang, Liwei, Han, Peng, Wen, Ji-Rong
Format: Article
Language:English
Subjects:
Image segmentation
Labels
Large-scale sparse learning (LSSL)
Matrix decomposition
Noise measurement
Noise reduction
noisy tags
Semantic segmentation
Semantics
Supervised learning
Symmetric matrices
Tags
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we present a large-scale sparse learning (LSSL) approach to solve the challenging task of semantic segmentation of images with noisy tags. Different from the traditional strongly supervised methods that exploit pixel-level labels for semantic segmentation, we make use of much weaker supervision (i.e., noisy tags of images) and then formulate the task of semantic segmentation as a weakly supervised learning (WSL) problem from the view point of noise reduction of superpixel labels. By learning the data manifolds, we transform the WSL problem into an LSSL problem. Based on nonlinear approximation and dimension reduction techniques, a linear-time-complexity algorithm is developed to solve the LSSL problem efficiently. We further extend the LSSL approach to visual feature refinement for semantic segmentation. The experiments demonstrate that the proposed LSSL approach can achieve promising results in semantic segmentation of images with noisy tags.
ISSN:2168-2267
2168-2275
DOI:10.1109/TCYB.2016.2631528