Deep learning models have been used extensively to solve real-world problems in recent years. The performance of such models relies heavily on large amounts of labeled data for training. While the advances of data collection technology have enabled the acquisition of a massive volume of data, labeling the data remains an expensive and time-consuming task. Active learning techniques are being progressively adopted to accelerate the development of machine learning solutions by allowing the model to query the data they learn from. In this paper, we introduce a real-world problem, the recognition of parking signs, and present a framework that combines active learning techniques with a transfer learning approach and crowd-sourcing tools to create and train a machine learning solution to the problem. We discuss how such a framework contributes to building an accurate model in a cost-effective and fast way to solve the parking sign recognition problem in spite of the unevenness of the data associated with the fact that street-level images (such as parking signs) vary in shape, color, orientation and scale, and often appear on top of different types of background.
1. Application of active learning approach to build a object detection system in iterative manner
2. How to select data for minority class from a pool of big dataset in an efficient way
3. Taking publicly available data and crowdsourcing the labelling in active learning framework to build useful system
1. Medium for Machine Learning Scientist/Data Scientist
2. Listener should know basic of Machine Learning and Deep Learning, Tensorflow, Python
Speaker: Humayun Irshad, Lead Machine Learning Scientist from Figure Eight.
more online AI tech talks: http://blog.xnextcon.com/?page_id=349