Deep Learning for Computer Vision - Lecture 15: Object Detection

Lecture 15 introduces object detection as the core computer vision task of localizing objects in images. We contrast this task with the image classification task we have mostly discussed so far, and see how we need new datasets (PASCAL, COCO), evaluation metrics (IoU, mAP), and neural network architectures to tackle this new task. We discuss the two-stage R-CNN family of methods for object detection including “slow” R-CNN, Fast R-CNN, and Faster R-CNN, and also briefly discuss single-stage approaches to object detection. Slides: http://myumi.ch/r80Pz _________________________________________________________________________________________________ Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification and object detection. Recent developments in neural network approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of neural-network based deep learning methods for computer vision. During this course, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. We will cover learning algorithms, neural network architectures, and practical engineering tricks for training and fine-tuning networks for visual recognition tasks. Course Website: http://myumi.ch/Bo9Ng Instructor: Justin Johnson http://myumi.ch/QA8Pg