Back to Search
Start Over
Towards weakly-supervised focus region detection via recurrent constraint network.
- Source :
-
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society [IEEE Trans Image Process] 2019 Sep 25. Date of Electronic Publication: 2019 Sep 25. - Publication Year :
- 2019
- Publisher :
- Ahead of Print
-
Abstract
- 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.
Details
- Language :
- English
- ISSN :
- 1941-0042
- Database :
- MEDLINE
- Journal :
- IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
- Publication Type :
- Academic Journal
- Accession number :
- 31562089
- Full Text :
- https://doi.org/10.1109/TIP.2019.2942505