YoVDO

Attacking Optical Flow

Offered By: Andreas Geiger via YouTube

Tags

Adversarial Attacks Courses Image Classification Courses Optical Flow Courses Deep Neural Networks Courses Semantic Segmentation Courses

Course Description

Overview

Explore a keynote presentation on attacking optical flow in deep neural networks for automated driving safety. Delve into the vulnerability of state-of-the-art optical flow estimation techniques to adversarial attacks, particularly focusing on patch attacks that can significantly compromise performance. Examine the differences in susceptibility between encoder-decoder and spatial pyramid network architectures. Learn about various types of attacks, including white-box, black-box, and real-world scenarios, as well as their implications for self-driving technology. Gain insights into the importance of robust artificial intelligence in safety-critical applications and the challenges of situational driving and data aggregation.

Syllabus

Intro
Collaborators
Self-Driving must be Robust
Situational Driving
Data Aggregation
Adversarial Attacks on Image Classification
Adversarial Attacks on Semantic Segmentation
Physical Adversarial Attacks
Robust Adversarial Attacks
Adversarial Patch Attacks
Low-Level Perception
Motion Estimation
Variational Optical Flow
Encoder-Decoder Networks
Spatial Pyramid Networks
Motivation
Attacking Optical Flow
White Box Attacks
Black-Box Attacks
Real-World Attack
Zero-Flow Test
Summary


Taught by

Andreas Geiger

Related Courses

Sequences, Time Series and Prediction
DeepLearning.AI via Coursera
A Beginners Guide to Data Science
Udemy
Artificial Neural Networks(ANN) Made Easy
Udemy
Makine Mühendisleri için Derin Öğrenme
Udemy
Customer Analytics in Python
Udemy