Italy

Advancements in reliable navigation and mapping rest to a large extent on robust, efficient and scalable understanding of the surrounding environment. The success in recent years have been propelled by the use machine learning techniques for capturing geometry and semantics of environment from video and range sensors. I will discuss approaches object detection, pose recovery, 3D reconstruction and detailed semantic parsing using deep convolutional neural networks (CNNs) as well as challenges of deploying these systems in real-world settings. To overcome the need for large amount of labeled data for training object instance detectors we use active self-supervision provided by a robot traversing an environment and generate training examples for learning novel object embeddings from unlabelled data. The object detectors trained in this manner achieve higher mAP compared to off-the-shelf detectors trained on this limited data. While perception and decision making are often considered separately, I will outline few strategies for jointly optimizing perception and decision making algorithms in the context of elementary navigation tasks. The presented explorations open interesting avenues for control of embodied physical agents and general strategies for design and development of general purpose autonomous systems.

IMPROVE 2022

Challenges and Opportunities in Autonomous Navigation

IMPROVE is a comprehensive conference of academic and technical nature, focused on image processing and computer vision practical applications. It brings together researchers, engineers and practitioners working either in fundamental areas of image processing, developing new methods and techniques, including innovative machine learning approaches, as well as multimedia communications technology and applications of image processing and artificial vision in diverse areas.

keynote

In many computer vision applications, the following problem arises: a collection of observations is interpreted as multiple noisy instances of different classes of objects. The observations can be 2D keypoints in an RG B image, 3D points in lidar scans, 2D-2D point correspondences in stereo matching, trajectories in tracking, etc. The classeses of object can be 2D or 3D geometric entitities like lines and planes, or transformations and relations between images. We will review recent techniques, mainly based on the RANSAC approach, for estimation of single and multiple instances of such object and demostrate their performance on a range of practical problems.

Robust Fitting in Computer Vision

In 1948, Shannon published a famous paper, which laid the foundations of information theory and led to a revolution in communication technologies. Critical to Shannon’s ideas was the notion that a signal can be represented in terms of “bits,” and that the information content of the signal can be measured by the minimum expected number of bits. However, while such a notion of information is well suited for tasks such as signal compression and reconstruction, it is not directly applicable to audio-visual scene interpretation tasks, because bits do not depend on the “semantic content” of the signal, such as words in a document, or objects in an image. In this talk, I will present a new measure of semantic information content called “semantic entropy”, which is defined as the minimum expected number of semantic queries about the data whose answers are sufficient for solving a given task (e.g., classification). I will also present an information-theoretic framework called ``information pursuit'' for deciding which queries to ask and in which order, which requires a probabilistic generative model relating data and questions to the task. Experiments on handwritten digit classification show, for example, that the translated MNIST dataset is harder to classify than the MNIST dataset. Joint work with Aditya Chattopadhyay, Benjamin Haeffele and Donald Geman.

Semantic Information Pursuit

In this talk, I will make connections between Graph Neural Networks (GNNs) and non-Euclidean diffusion equations. I will show that drawing on methods from the domain of differential geometry, it is possible to provide a principled view on such GNN architectural choices as positional encoding and graph rewiring as well as explain and remedy the phenomena of oversquashing and bottlenecks.

Downloads

Next from IMPROVE 2022

Robust Fitting in Computer Vision

Similar lecture

Robust Fitting in Computer Vision

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from IMPROVE 2022

Robust Fitting in Computer Vision

Similar lecture

Robust Fitting in Computer Vision

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads