Background Invariance By Adversarial Learning
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2020)
摘要
Convolutional neural networks are shown to be vulnerable to changes in the background. The proposed method is an end-to-end method that augments the training set by introducing new backgrounds during the training process. These backgrounds are created by a generative network that is trained as an adversary to the model. A case study is explored based on overhead power line insulators detection using a drone - a training set is prepared from photographs taken inside a laboratory and then evaluated using photographs that are harder to collect from outside the laboratory. The proposed method improves performance by over 20% for this case study.
更多查看译文
关键词
adversarial learning,convolutional neural networks,end-to-end method,training set,generative network,overhead power line insulators detection,photographs,background invariance
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要