Paper Info
Title
Learn to Differ: Sim2Real Small Defection Segmentation Network
Abstract
Recent studies on deep-learning-based small defection segmentation approaches are trained in specific settings and tend to be limited by fixed context. Throughout the training, the network inevitably learns the representation of the background of the training data before figuring out the defection. They underperform in the inference stage once the context changed and can only be solved by training in every new settings. This eventually leads to the limitation in practical robotic applications where contexts keep varying. To cope with this, instead of training a network context by context and hoping it to generalize, why not stop misleading it with any limited context and start training it with pure simulation? In this paper, we propose the network SSDS that learns a way of distinguishing small defections between two images regardless of the context, so that the network can be trained once for all. A small defection detection layer utilizing the pose sensitivity of phase correlation between images is introduced and is followed by an outlier masking layer. The network is trained on randomly generated simulated data with simple shapes and is generalized across the real world. Finally, SSDS is validated on real-world collected data and demonstrates the ability that even when trained in cheap simulation, SSDS can still find small defections in the real world showing the effectiveness and its potential for practical applications. Code is available here
Year
DOI
Venue
2021
10.1109/IROS51168.2021.9636491
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
DocType
ISSN
Citations 
Conference
2153-0858
0
PageRank 
References 
Authors
0.34
0
9
Name
Order
Citations
PageRank
Zexi Chen103.72
Zheyuan Huang202.70
Hongxiang Yu300.34
Zhongxiang Zhou400.68
Yunkai Wang501.69
Xuecheng Xu612.72
Qimeng Tan712.38
Yue Wang826040.39
Rong Xiong97722.86