ClickBAIT: Click-based Accelerated Incremental Training of Convolutional Neural Networks

09/15/2017
by   Ervin Teng, et al.
0

Today's 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.

READ FULL TEXT

page 4

page 7

page 8

page 9

page 10

research
03/27/2018

ClickBAIT-v2: Training an Object Detector in Real-Time

Modern deep convolutional neural networks (CNNs) for image classificatio...
research
05/04/2019

Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading

We focus on the word-level visual lipreading, which requires recognizing...
research
01/04/2019

Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video

In Intelligent Transportation System, real-time systems that monitor and...
research
02/23/2018

Real-Time End-to-End Action Detection with Two-Stream Networks

Two-stream networks have been very successful for solving the problem of...
research
01/19/2015

Transferring Rich Feature Hierarchies for Robust Visual Tracking

Convolutional neural network (CNN) models have demonstrated great succes...
research
08/30/2016

Motion Representation with Acceleration Images

Information of time differentiation is extremely important cue for a mot...
research
03/03/2018

Real-Time Deep Learning Method for Abandoned Luggage Detection in Video

Recent terrorist attacks in major cities around the world have brought m...

Please sign up or login with your details

Forgot password? Click here to reset