Modern deep convolutional neural networks (CNNs) for image classification and object detection are often trained offline on large static datasets. Some applications, however, will require training in real-time on live video streams with a human-in-the-loop. We refer to this class of problem as time-ordered online training (ToOT). These problems will require a consideration of not only the quantity of incoming training data, but the human effort required to annotate and use it. We demonstrate and evaluate a system tailored to training an object detector on a live video stream with minimal input from a human operator. We show that we can obtain bounding box annotation from weakly-supervised single-point clicks through interactive segmentation. Furthermore, by exploiting the time-ordered nature of the video stream through object tracking, we can increase the average training benefit of human interactions by 3-4 times.
@article{arxiv.1803.10358,
title = {ClickBAIT-v2: Training an Object Detector in Real-Time},
author = {Ervin Teng and Rui Huang and Bob Iannucci},
journal= {arXiv preprint arXiv:1803.10358},
year = {2018}
}
Comments
8 pages, 13 figures. For ClickBAIT-v1, see arXiv:1709.05021