Domain Adaptation from Synthesis to Reality in Single-model Detector for Video Smoke Detection
arXiv:1709.08142
Abstract
This paper proposes a method for video smoke detection using synthetic smoke samples. The virtual data can automatically offer precise and rich annotated samples. However, the learning of smoke representations will be hurt by the appearance gap between real and synthetic smoke samples. The existed researches mainly work on the adaptation to samples extracted from original annotated samples. These methods take the object detection and domain adaptation as two independent parts. To train a strong detector with rich synthetic samples, we construct the adaptation to the detection layer of state-of-the-art single-model detectors (SSD and MS-CNN). The training procedure is an end-to-end stage. The classification, location and adaptation are combined in the learning. The performance of the proposed model surpasses the original baseline in our experiments. Meanwhile, our results show that the detectors based on the adversarial adaptation are superior to the detectors based on the discrepancy adaptation. Code will be made publicly available on http://smoke.ustc.edu.cn. Moreover, the domain adaptation for two-stage detector is described in Appendix A.
The manuscript approved by all authors is our original work, and has submitted to Pattern Recognition for peer review previously. There are 4532 words, 6 figures and 1 table in this manuscript
References in corpus (7)
- Learning Transferable Features with Deep Adaptation Networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- Focal Loss for Dense Object Detection
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
- Deep Domain Adaptation Based Video Smoke Detection using Synthetic Smoke Images
- Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation