Lecture

Uncertainty Quantification and Label Error Detection

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture by the instructor covers the topics of uncertainty quantification and label error detection for semantic segmentation in deep learning. It discusses the challenges of false positives, false negatives, and label errors in datasets, as well as methods for detecting errors and estimating prediction quality. The lecture also explores the use of active learning, meta learning, and automated architecture search in deep learning applications. Various research tracks and further applications are presented, including the importance of mastering perception for automation in safety-critical fields like automated driving and medical imaging.

Official source

Ontological neighbourhood

Information engineering

Artificial intelligence: Computer vision

Related concepts (32)

Object detection

Object detection is a computer technology related to computer vision and that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos. Well-researched domains of object detection include face detection and pedestrian detection. Object detection has applications in many areas of computer vision, including and video surveillance. It is widely used in computer vision tasks such as , vehicle counting, activity recognition, face detection, face recognition, video object co-segmentation.

Experiential learning

Experiential learning (ExL) is the process of learning through experience, and is more narrowly defined as "learning through reflection on doing". Hands-on learning can be a form of experiential learning, but does not necessarily involve students reflecting on their product. Experiential learning is distinct from rote or didactic learning, in which the learner plays a comparatively passive role. It is related to, but not synonymous with, other forms of active learning such as action learning, adventure learning, free-choice learning, cooperative learning, service-learning, and situated learning.

Active learning

Active learning is "a method of learning in which students are actively or experientially involved in the learning process and where there are different levels of active learning, depending on student involvement." states that "students participate [in active learning] when they are doing something besides passively listening." According to Hanson and Moser (2003) using active teaching techniques in the classroom can create better academic outcomes for students.

Vehicular automation

Vehicular automation involves the use of mechatronics, artificial intelligence, and multi-agent systems to assist the operator of a vehicle (car, aircraft, watercraft, or otherwise). These features and the vehicles employing them may be labeled as intelligent or smart. A vehicle using automation for difficult tasks, especially navigation, to ease but not entirely replace human input, may be referred to as semi-autonomous, whereas a vehicle relying solely on automation is called robotic or autonomous.

Self-driving car

A self-driving car, also known as an autonomous car, driverless car, or robotic car (robo-car), is a car that is capable of traveling without human input. Self-driving cars use sensors to perceive their surroundings, such as optical and thermographic cameras, radar, lidar, ultrasound/sonar, GPS, odometry and inertial measurement units. Control systems interpret sensory information to create a three-dimensional model of the vehicle's surroundings.

Related lectures (64)

Machine Learning Fundamentals

Covers fundamental principles, opportunities, and challenges in machine learning.

Deep Learning: Edge Detection and Neural Networks

Discusses edge detection techniques and the evolution of deep learning in neural networks.

Convolutional Neural Networks

Introduces Convolutional Neural Networks (CNNs) for autonomous vehicles, covering architecture, applications, and regularization techniques.

Proper Feature Size: Image Analysis MOOC: Image Processing and Analysis for Life Scientists

Delves into choosing a proper feature size for image analysis in life sciences, presenting a Rule Of Thumb for defining object size in pixels.

Active Learning for Molecular Design