Title
Box-Driven Class-Wise Region Masking And Filling Rate Guided Loss For Weakly Supervised Semantic Segmentation
Abstract
Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional Networks (FCN). However, the performance of FCN based models severely rely on the amounts of pixel-level annotations which are expensive and time-consuming. To address this problem, it is a good choice to learn to segment with weak supervision front bounding boxes. How to make full use of the class-level and region-level supervisions from bounding boxes is the critical challenge for the weakly supervised learning task. In this paper, we first introduce a box-driven class-wise masking model (BCM) to remove irrelevant regions of each class. Moreover, based on the pixel-level segment proposal generated from the bounding box supervision, we could calculate the mean filling rates of each class to serve as an important prior cue, then we propose a filling rate guided adaptive loss (FR-Loss) to help the model ignore the wrongly labeled pixels in proposals. Unlike previous methods directly training models with the fixed individual segment proposals, our method can adjust the model learning with global statistical information. Thus it can help reduce the negative impacts from wrongly labeled proposals. We evaluate the proposed method on the challenging PASCAL VOC 2012 benchmark and compare with other methods. Extensive experimental results show that the proposed method is effective and achieves the state-of-the-art results.
Year
DOI
Venue
2019
10.1109/CVPR.2019.00325
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
Field
DocType
Volume
Masking (art),Pattern recognition,Segmentation,Computer science,Supervised learning,Pixel,Artificial intelligence,Machine learning,Minimum bounding box,Model learning,Bounding overwatch
Journal
abs/1904.11693
ISSN
Citations 
PageRank 
1063-6919
10
0.45
References 
Authors
0
4
Name
Order
Citations
PageRank
Chunfeng Song1548.53
Yan Huang222627.65
Wanli Ouyang32371105.17
Liang Wang44317243.28