Please use this identifier to cite or link to this item:
Title: Self-supervised online metric learning with low rank constraint for scene categorization
Authors: Cong, Yang
Liu, Ji
Yuan, Junsong
Luo, Jiebo
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Issue Date: 2013
Source: Cong, Y., Liu, J., Yuan, J., & Luo, J. (2013). Self-supervised Online Metric Learning with Low Rank Constraint for Scene Categorization. IEEE Transactions on Image Processing, 22(8), 3179-3191.
Series/Report no.: IEEE transactions on image processing
Abstract: Conventional visual recognition systems usually train an image classifier in a bath mode with all training data provided in advance. However, in many practical applications, only a small amount of training samples are available in the beginning and many more would come sequentially during online recognition. Because the image data characteristics could change over time, it is important for the classifier to adapt to the new data incrementally. In this paper, we present an online metric learning method to address the online scene recognition problem via adaptive similarity measurement. Given a number of labeled data followed by a sequential input of unseen testing samples, the similarity metric is learned to maximize the margin of the distance among different classes of samples. By considering the low rank constraint, our online metric learning model not only can provide competitive performance compared with the state-of-the-art methods, but also guarantees convergence. A bi-linear graph is also defined to model the pair-wise similarity, and an unseen sample is labeled depending on the graph-based label propagation, while the model can also self-update using the more confident new samples. With the ability of online learning, our methodology can well handle the large-scale streaming video data with the ability of incremental self-updating. We evaluate our model to online scene categorization and experiments on various benchmark datasets and comparisons with state-of-the-art methods demonstrate the effectiveness and efficiency of our algorithm.
ISSN: 1057-7149
DOI: 10.1109/TIP.2013.2260168
Rights: © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Citations 50

Updated on Jan 10, 2021

Citations 50

Updated on Jan 11, 2021

Page view(s) 50

Updated on Jan 16, 2021

Download(s) 5

Updated on Jan 16, 2021

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.