Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation
Lists
Only you see this
Abstract
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.
BibTeX
@article{li2018large,
author = {Aoxue Li and Zhiwu Lu and Liwei Wang and Peng Han and Ji-Rong Wen},
title = {{Large-Scale Sparse Learning From Noisy Tags for Semantic Segmentation}},
journal = {IEEE Trans. Cybernetics},
year = {2018},
doi = {10.1109/tcyb.2016.2631528},
}Loading related content...