Fast and Easy Sensor Adaptation With Self-Training

Abstract

Object detectors based on deep neural networks have the disadvantage that new labels should be acquired whenever the complementary metal-oxide semiconductor (CMOS) image sensor (CIS) is changed. In this study, we propose a fast and easy two-step sensor-adaptation method without labels for the target domain; 1) simple adaptation, and 2) self-training. The simple-adaptation process transfers the knowledge of the source model to the target model by updating the batch normalization parameters, and matches the feature distributions of the source domain and those of target domain. In the self-training process, we employ the ensemble model strategy to mitigate the over-fitting problem using noisy pseudo labels generated by the simple-adaptation model. Quantitative and qualitative experiments show that the proposed method can transfer the knowledge from one CIS model to another, even if the data format of the target domain is different from that of the source CIS domain.

Keywords

• Domain adaptation
• raw image
• self-training
• semi-supervised learning
• sensor adaptation