In this Computer Vision course, we will learn how to process and work with images for Image classification using Neural Networks. Going beyond plain Neural Networks, we will also learn a more advanced architecture – Convolutional Neural Networks.
Introduction to Image data
This module will teach you how to process the image and extract all the data from it, which can be used for image recognition in deep learning.
Introduction to Convolutional Neural Networks
Convolutional Neural Networks (CNN) are used for image processing, classification, segmentation, and many more applications. This module will help you learn everything about CNN.
Famous CNN architectures
In this module, you will learn everything you need to know about several CNN architectures like AlexNet, GoogLeNet, VGGNet, etc.
Transfer learning is a research problem in deep learning that focuses on storing knowledge gained while training one model and applying it to another model.
Object detection is a computer vision technique in which a software system can detect, locate, and trace objects from a given image or video. Face detection is one of the examples of object detection. You will learn how to detect any object using deep learning algorithms in this module.
The goal of semantic segmentation (also known as dense prediction) in computer vision is to label each pixel of the input image with the respective class representing a specific object/body.
Object Instance Segmentation takes semantic segmentation one step ahead in a sense that it aims towards distinguishing multiple objects from a single class. It is considered as a Hybrid of Object Detection and Semantic Segmentation tasks.
Other variants of convolution
This module will drive you several other essential variants in Convolutional Neural Networks (CNN).
Metric Learning is a task of learning distance metrics from supervised data in a machine learning manner. It focuses on computer vision and pattern recognition.
A Siamese neural network (sometimes called a twin neural network) is an artificial neural network that contains two or more identical subnetworks which means they have the same configuration with the same parameters and weights. This module will help you find the similarity of the inputs by comparing the feature vectors of subnetworks.
In learning a projection where the inputs can be distinguished, the triplet loss is similar to metric learning. The triplet loss is used for understanding the score vectors for the images. You can use the score vectors of face descriptors for verifying the faces in Euclidean Space.