06-17, 11:00–12:30 (Europe/London), Tower Suite 1
Object detection, the task of localising and classifying objects in a scene, one of the most popular tasks in Computer Vision, has a main drawback: a large annotated dataset is necessary to train the model. Indeed, annotating a dataset is expensive, and the free available datasets are not enough, as they do not contain all the classes we are interested in. Thus, the goal of the tutorial is to introduce the main techniques to train a good object detector utilising the minimum amount of annotated data.
The goals of the tutorial can be summarised in the following points: 1. Introduce deep learning-based object detector models. 2. Show the power of transfer learning: few new data are necessary if the model has been pretrained on a large dataset. 3. Define the properties of a good dataset (i.e., maximal entropy), and describe how to obtain it. The tutorial is for those interested in deep and transfer learning or who want to learn more about it. No prior knowledge of computer vision is required.
Previous knowledge expected
