Please use this identifier to cite or link to this item:
Title: Online active proposal set generation for weakly supervised object detection
Authors: Jin, Ruibing
Lin, Guosheng
Wen, Changyun
Keywords: Engineering::Electrical and electronic engineering
Engineering::Computer science and engineering
Issue Date: 2022
Source: Jin, R., Lin, G. & Wen, C. (2022). Online active proposal set generation for weakly supervised object detection. Knowledge-Based Systems, 237, 107726-.
Project: 04INS000338C130 
RG28/18 (S) 
RG22/19 (S) 
Journal: Knowledge-Based Systems 
Abstract: To reduce the manpower consumption on box-level annotations, many weakly supervised object detection methods which only require image-level annotations, have been proposed recently. The training process in these methods is formulated into two steps. They firstly train a neural network under weak supervision to generate pseudo ground truths (PGTs). Then, these PGTs are used to train another network under full supervision. Compared with fully supervised methods, the training process in weakly supervised methods becomes more complex and time-consuming. Furthermore, overwhelming negative proposals are involved at the first step. This is neglected by most methods, which makes the training network biased towards to negative proposals and thus degrades the quality of the PGTs, limiting the training network performance at the second step. Online proposal sampling is an intuitive solution to these issues. However, lacking of adequate labeling, a simple online proposal sampling may make the training network stuck into local minima. To solve this problem, we propose an Online Active Proposal Set Generation (OPG) algorithm. Our OPG algorithm consists of two parts: Dynamic Proposal Constraint (DPC) and Proposal Partition (PP). DPC is proposed to dynamically determine different proposal sampling strategies according to the current training state. PP is used to score each proposal, part proposals into different sets and generate an active proposal set for the network optimization. Through experiments, our proposed OPG shows consistent and significant improvement on both datasets PASCAL VOC 2007 and 2012, yielding comparable performance to the state-of-the-art results.
ISSN: 0950-7051
DOI: 10.1016/j.knosys.2021.107726
Schools: School of Computer Science and Engineering 
School of Electrical and Electronic Engineering 
Rights: © 2021 Elsevier B.V. All rights reserved. This paper was published in Knowledge-Based Systems and is made available with permission of Elsevier B.V.
Fulltext Permission: embargo_20240222
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles
SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
Online Active Proposal Set Generation for Weakly.pdf
  Until 2024-02-22
5.6 MBAdobe PDFUnder embargo until Feb 22, 2024

Citations 50

Updated on Sep 16, 2023

Web of ScienceTM
Citations 50

Updated on Sep 17, 2023

Page view(s)

Updated on Sep 19, 2023

Google ScholarTM




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