The First key speaker:
Dr. Ricardo Carmona Galán, from the Institute of Instituto de Microelectrónica de Sevilla IMSE-CNM at CoSeRa 2024 on 18th-20th September 2024, in Santiago de Compostela (Spain), where he will share their recent advances on compressive sampling for image-to-decision on the sensor chip:
He received the degrees of Licenciado (B. Sc.) and Doctor (Ph. D.) in Physics, in the speciality of Electronics, both from the Universidad de Sevilla, Spain. His main research areas are vision chips, in particular, smart cmos imagers for low-power vision applications like robotics , vehicle navigation and vision-enabled wireless sensor networks. He is also interested in CMOS-compatible sensing structures for LWIR and MWIR imaging, single photon detection, and detectors for xray and high energy physics.
Talk Title: Visual information cues from a CMOS front-end sensor chip
Talk Abstract: CMOS image sensors are widely used in digital cameras and mobile phones due to their low power consumption, high speed and the capability of integrating multiple functionalities. The major drive for their development has been increasing spatial and temporal resolution. All the pixels need to be sampled and digitized before any visual processing can take place. However, many application scenarios like autonomous driving, augmented and virtual reality, and the AIoT, would benefit from an earlier and more efficient processing of the visual information. And we know that object recognition and classification does not rely on prescribed features anymore. The deep learning approach has revolutionized recognition by outdoing human accuracy for some tests, but this has been achieved at the expense of a considerable power and a large amount of computing and memory resources. In this talk we will exploit compressive sampling to extract the relevant content of the visual stimulus right at the sensor chip, thus allowing a lightweight and power-aware implementation of high-level inference.
The Second key speaker:
Prof. Fauzia Ahmad, from the Temple University :
Prof. Fauzia Ahmad received her Ph.D. degree in Electrical Engineering in 1997 from the University of Pennsylvania, Philadelphia. Currently, she is an Associate Professor in the Electrical and Computer Engineering Department and Director of the Multi-modal Sensing and Imaging (MSI) Lab at the College of Engineering, Temple University, Philadelphia.
Her research interests lie in the areas of array and statistical signalprocessing , computational_imaging with applications in radar and ultrasonics, compressive sensing , machinelearning , waveform design, radar systems including SAR, MIMO radar and passive radar, and structural heath monitoring.
Talk Title: Near-field Radar Imaging – From Physics-Based to Learning-Based Frameworks
Talk Abstract: Many modern radar applications do not conform to the far-field propagation model, with a primary departure being spherical instead of planar wavefronts. The wavefront curvature has a major impact on system performance and must be considered in the scene reconstruction procedure for effective and reliable imaging. Near-field imaging techniques are, therefore, essential for short-range applications, such as ground-penetrating radar, biomedical radar, and automotive radar. Popular frameworks for solving near-field radar imaging problems include high-resolution subspace-based, sparse reconstruction, and more recently learning-based frameworks. This talk aims to provide an overview of these nearfield image reconstruction frameworks and offers several illustrating examples in diverse radar applications.
The Third key speaker:
Dr. Mahdi Soltanolkotabi, from the University of Southern California:
Dr. Mahdi Soltanolkotabi is an associate professor in the Ming Hsieh Department of Electrical and Computer Engineering, Computer Science, and Industrial and Systems Engineering (ISE) at the University of Southern California. Prior to joining USC he spent a year as a postdoc in the AMPLab at University of California, Berkeley. He obtained his Ph.D. in Electrical Engineering from Stanford University in 2014.
His research focuses on developing the mathematical foundations of learning from signals and data spanning optimization, machinelearning , signalprocessing , high dimensional probability/statistics, computational_imaging and artificialintelligence . Over the last few years, he has been developing and analyzing algorithms for non-convex optimization with provable guarantees of convergence to generalizable global optima including those arising in deeplearning . A particular focus on the application side has been on developing AI for scientific applications in areas such as computational_imaging, medicalimaging and wireless_systems.
Talk Title: Theoretical Foundations of Feature Learning
Talk Abstract: One of the major transformations in modern learning is that contemporary models trained through gradient descent have the ability to learn versatile representations that can then be applied effectively across a broad range of down-stream tasks. Existing theory however suggests that neural networks, when trained via gradient descent, behave similar to kernel methods that fail to learn representations that can be transferred. In the first part of this talk I will try to bridge this discrepancy by showing that gradient descent on neural networks can indeed learn a broad spectrum of functions that kernel methods struggle with, by acquiring task-relevant representations. In the second part of the talk I will focus on feature learning in prompt-tuning which is an emerging strategy to adapt large language models (LLM) to downstream tasks by learning a (soft-)prompt parameter from data. We demystify how prompt-tuning enables the model to focus attention to context-relevant information/features.
The Fourth key speaker:
Prof. Sabine Süsstrunk, from the EPFL – École Polytechnique Fédérale de Lausanne:
Prof. Sabine Süsstrunk leads the Image and Visual Representation Lab in the School of Computer and Communication Sciences (IC) at EPFL since 1999. From 2015-2020, she was also the first Director of the Digital Humanities Institute (DHI), College of Humanities (CdH).Her main research areas are in computational_photography, computational_imaging, color imageprocessing and computervision , machinelearning , and computational image quality and aesthetics.
Talk Title: On generating image and video hallucinations
Talk Abstract: “Hallucination” is a term used in the AI community to describe the plausible falsehoods produced by deep generative neural networks. It is often considered a negative, especially in relation with large language models or medical image reconstruction. Yet, in many computational photography applications, we rely on such hallucinations to create pleasing images. It often does not matter if all (or any) information was present in the real world if the produced falsehoods are visually plausible. Starting from that premise, I will present our recent work on hallucinations in image reconstruction, image style creation, and texture synthesis, using different generative models such as diffusion networks, neural radiance fields, and neural cellular automata. With a nod to the dangers some of these hallucinations might pose, I will also briefly discuss our work on deep fake detection.
Recent Comments