Towards Weakly-Supervised Focus Region Detection via Recurrent Constraint Network

Recent state-of-the-art methods on focus region detection (FRD) rely on deep convolutional networks trained with costly pixel-level annotations. In this study, we propose a FRD method that achieves competitive accuracies but only uses easily obtained bounding box annotations. Box-level tags provide...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2020-01, Vol.29, p.1356-1367
Main Authors: Zhao, Wenda, Hou, Xueqing, Yu, Xiaobing, He, You, Lu, Huchuan
Format: Article
Language:English
Subjects:
Annotations
box-level supervision
Conditional random fields
Datasets
Dogs
Focus region detection
fully convolutional network
Image segmentation
Object segmentation
Pixels
recurrent constraint network
Semantics
Tags
Task analysis
Training
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:Recent state-of-the-art methods on focus region detection (FRD) rely on deep convolutional networks trained with costly pixel-level annotations. In this study, we propose a FRD method that achieves competitive accuracies but only uses easily obtained bounding box annotations. Box-level tags provide important cues of focus regions but lose the boundary delineation of the transition area. A recurrent constraint network (RCN) is introduced for this challenge. In our static training, RCN is jointly trained with a fully convolutional network (FCN) through box-level supervision. The RCN can generate a detailed focus map to locate the boundary of the transition area effectively. In our dynamic training, we iterate between fine-tuning FCN and RCN with the generated pixel-level tags and generate finer new pixel-level tags. To boost the performance further, a guided conditional random field is developed to improve the quality of the generated pixel-level tags. To promote further study of the weakly supervised FRD methods, we construct a new dataset called FocusBox, which consists of 5000 challenging images with bounding box-level labels. Experimental results on existing datasets demonstrate that our method not only yields comparable results than fully supervised counterparts but also achieves a faster speed.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2019.2942505