Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/79795
Title: Active self-paced learning for cost-effective and progressive face identification
Authors: Lin, L
Wang, KZ
Meng, DY
Zuo, WM
Zhang, L 
Keywords: Cost-effective model
Active learning
Self-paced learning
Incremental processing
Face identification
Issue Date: 2018
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on pattern analysis and machine intelligence, Jan. 2018, v. 40, no. 1, p. 7-19 How to cite?
Journal: IEEE transactions on pattern analysis and machine intelligence 
Abstract: This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert recertification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a number of candidates are selected from the unannotated samples for classifier updating, in which we apply the current classifiers ranking the samples by the prediction confidence. In particular, our approach utilizes the high-confidence and low-confidence samples in the self-paced and the active user-query way, respectively. The neural nets are later fine-tuned based on the updated classifiers. Such heuristic implementation is formulated as solving a concise active SPL optimization problem, which also advances the SPL development by supplementing a rational dynamic curriculum constraint. The new model finely accords with the "instructor-student-collaborative" learning mode in human education. The advantages of this proposed framework are two-folds: i) The required number of annotated samples is significantly decreased while the comparable performance is guaranteed. A dramatic reduction of user effort is also achieved over other state-of-the-art active learning techniques. ii) The mixture of SPL and AL effectively improves not only the classifier accuracy compared to existing AL/SPL methods but also the robustness against noisy data. We evaluate our framework on two challenging datasets, which include hundreds of persons under diverse conditions, and demonstrate very promising results. Please find the code of this project at: http://hcp.sysu.edu.cn/projects/aspl/
URI: http://hdl.handle.net/10397/79795
ISSN: 0162-8828
EISSN: 1939-3539
DOI: 10.1109/TPAMI.2017.2652459
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

23
Citations as of Apr 3, 2019

WEB OF SCIENCETM
Citations

15
Last Week
0
Last month
Citations as of Apr 6, 2019

Page view(s)

16
Citations as of Apr 23, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.