Rating 4.88 out of 5 (4 ratings in Udemy)
What you'll learn- Get newest state-of-the-art Computer vision (CV) Deep-learning knowledge
- Be able to start research at Computer-vision with Deep-learning
- Be able to start engineering at Computer-vision with Deep-learning
- Be able to teach Computer-vision with Deep-learning
DescriptionHello I am Nitsan Soffair, A Deep RL researcher at BGU.
In this Computer-vision course, you will learn the newest state-of-the-art Computer vision (CV) …
Rating 4.88 out of 5 (4 ratings in Udemy)
What you'll learn- Get newest state-of-the-art Computer vision (CV) Deep-learning knowledge
- Be able to start research at Computer-vision with Deep-learning
- Be able to start engineering at Computer-vision with Deep-learning
- Be able to teach Computer-vision with Deep-learning
DescriptionHello I am Nitsan Soffair, A Deep RL researcher at BGU.
In this Computer-vision course, you will learn the newest state-of-the-art Computer vision (CV) Deep-learning knowledge.
You will do the following
Get state-of-the-art knowledge of the following
Object detection
Image segmentation
Visualization and Interpretability
Validate your knowledge by answering short and very easy 3-question queezes of each lecture
Be able to complete the course by ~2 hours.
Syllabus
Introduction to Computer vision
Classification and Object detection
Technology in the field of computer vision for finding and identifying objects in an image or video sequence
Segmentation
The process of partitioning a digital image into multiple image segments of pixels' sets.
Transfer-learning
A research problem in machine learning (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem.
Resnets
An artificial neural network (ANN). Skip connections are used to jump over some layers.
Object localization
a computer technology to detect instances of semantic objects of a certain class i.e. humans, buildings in images and videos.
Object detection
R-CNN
Detection algorithm.
Fast R-CNN
Detection network region-proposal algorithm.
Faster R-CNN
Object detection network region-proposal algorithm.
RetinaNet
A dense detector evaluating the loss.
Image segmentation
FCN
Transforms image pixels to classes using CNN.
Upsampling methods
Performed on a sequence of signal's samples/continuous function.
Evaluation with IoU and Dice-score
Evaluation metrics.
U-Net
A Deep neural-networl model based on fully-connected neural-network.
Visualization and Interpretability
Class activation maps
Technique gets the discriminative image regions used by CNN to identify specific classes in image.
Saliency maps
An image that highlights the region on which people's eyes focus first.
Resources
