Oct 2023 Computer Vision Meetup (Virtual - EU and Americas)

Zoom Link

https://voxel51.com/computer-vision-events/october-computer-vision-meetup-americas-emea/

Bridging the Gap: Advancing Civil Engineering Inspections with Computer Vision

Civil engineering structures such as power plants, sewers, and bridges form essential components of the public infrastructure. It is mandatory to keep these structures in a safe and operational state. In order to ensure this, they are frequently inspected where the current recognition and documentation of defects and building components is mostly carried out manually. A failure of individual structures results in enormous costs. For example, the economic costs caused by the closure of a bridge due to congestion is many times the cost of the bridge itself and its maintenance.Recent advancements in hardware and software offer great potential for increasing the quality, traceability, and efficiency of the structural inspection process. In particular, methods from the field of computer vision play an important role. The new techniques support the inspection engineer at the building site, raising quality and efficiency of the inspection. There is a high demand worldwide for the automation of structural inspections in the areas of building construction, bridge construction, tunnel construction, sewage plants, and other critical infrastructures.In this talk Johannes will introduce the audience to visual defect recognition on buildings. Also highlighted will be the workshop at WACV 2024 and the hosted challenge, “dacl-challenge”.

Speaker: Johannes Flotzinger is a Civil Engineer and Research assistant at Universität der Bundeswehr München.

Adapting to Change: Foundation Models, APIs, and the Past, Present and Future of AI Development

This talk presents a reflection over the evolving landscape of AI development, focusing on the transition from individual small models, served on cloud or prem infrastructure – to the contemporary era characterized by the prominence of foundation models and APIs. The talk delves into the practical implications of these shifts, emphasizing their impact on AI development strategies, touching pros and cons, as well as data and privacy implications

Speaker: Pietro Bolcato is an experienced AI Engineer, holding a double master’s degree focused in Deep Learning and Artificial Intelligence from TU Berlin and KTH Stockholm. With years of experience ranging from the research field to startups, he has always focused on Generative AI – delivering end-to-end solutions, that are scalable, efficient and reproducible.

Deci Diffusion: Triple the Speed of Stable Diffusion

Introducing DeciDiffusion 1.0. A new text-to-image 820 million parameter text-to-image latent diffusion. The model trained is on the LAION-v2 dataset and fine-tuned on the LAION-ART dataset. While it maintains foundational architecture elements from Stable Diffusion, such as the Variational Autoencoder (VAE) and CLIP’s pre-trained Text Encoder, DeciDiffusion’s primary innovation is the substitution of U-Net with the more efficient U-Net-NAS. In this talk, I’ll dive into the architectural innovations and showcase DeciDiffusion in action!

Speaker: Harpreet Sahota is the Deep Learning Developer Relations Manager at Deci AI