Title | ||
---|---|---|
ClickBAIT: Click-based Accelerated Incremental Training of Convolutional Neural Networks. |
Abstract | ||
---|---|---|
Todayu0027s general-purpose deep convolutional neural networks (CNN) for image classification and object detection are 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 tag and use it. In this paper, we define training benefit as a metric to measure the effectiveness of a sequence in using each user interaction. We demonstrate and evaluate a system tailored to performing ToOT in the field, capable of training an image classifier on a live video stream through minimal input from a human operator. We show that by exploiting the time-ordered nature of the video stream through optical flow-based object tracking, we can increase the effectiveness of human actions by about 8 times. |
Year | Venue | Field |
---|---|---|
2017 | AIPR | Image classifier,Training set,Object detection,Human operator,Pattern recognition,Convolutional neural network,Computer science,Video tracking,Artificial intelligence,Contextual image classification,Optical flow,Machine learning |
DocType | Volume | Citations |
Journal | abs/1709.05021 | 1 |
PageRank | References | Authors |
0.37 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ervin Teng | 1 | 1 | 1.72 |
João Diogo Falcão | 2 | 1 | 0.37 |
Bob Iannucci | 3 | 41 | 10.62 |