Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Robust Vision: Data Augmentation and Ensembling Techniques

Description

This lecture covers various data augmentation techniques such as standard transforms, DeepAugment, stylization, domain randomization, 3D corruptions, AutoAugment, and AugMix. It also explores ensembling methods including deep ensembles and cross-domain ensembles, comparing ViT and ResNet models for image classification, and test-time adaptation strategies.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Official source

Related concepts (11)

Computer vision

Computer vision tasks include methods for , , and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context means the transformation of visual images (the input to the retina in the human analog) into descriptions of the world that make sense to thought processes and can elicit appropriate action.

Computer stereo vision

Computer stereo vision is the extraction of 3D information from digital images, such as those obtained by a CCD camera. By comparing information about a scene from two vantage points, 3D information can be extracted by examining the relative positions of objects in the two panels. This is similar to the biological process of stereopsis. In traditional stereo vision, two cameras, displaced horizontally from one another, are used to obtain two differing views on a scene, in a manner similar to human binocular vision.

Feature (computer vision)

In computer vision and , a feature is a piece of information about the content of an image; typically about whether a certain region of the image has certain properties. Features may be specific structures in the image such as points, edges or objects. Features may also be the result of a general neighborhood operation or feature detection applied to the image. Other examples of features are related to motion in image sequences, or to shapes defined in terms of curves or boundaries between different image regions.

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

Q-learning

Q-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.

Related lectures (32)

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Socially-aware Artificial Intelligence for Last-mile Mobility

Explores socially-aware AI for last-mile mobility, focusing on understanding social etiquettes, anticipating behaviors, and forecasting crowd movements.

Machine Learning Fundamentals

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

Machine Learning for Solving PDEs: Random Feature Method

Explores the Random Feature Method for solving PDEs using machine learning algorithms to approximate high-dimensional functions efficiently.

Deep Learning: Convolutional Neural Networks