BY AI BOOSTER
Computer VISIONers Conference
Computer VISIONers Conference is a hardcore conference for true computer vision engineers. The place where you discover newest trends, tools and best practices from leading experts in the field. Accelerate your knowledge with AI Booster!
We want to surprise you, so the full agenda coming soon! Stay tuned!
by Eugene Khvedchenya
What are the modest neural network architectures for binary, multiclass and instance segmentation? During the talk we will learn how to segment object from the background, find vehicles on satellite imagery and count nuclei cells on the radiology photography10:00 AM
by Pedro Porto Buarque de Gusmão
We will have a comprehensive overview on the previous state of the art and talk about deep learning approaches to visual odometry and SLAM in the context of firefighters (low visibility, smoke, etc).11:00 AM
by Sergiy Koshel
We will see how to build a custom computer vision system from scratch and how to deal with the lack of training data.12:00 AM
by Vincenzo Lomonaco
Continual Learning (CL) is a fast emerging topic in AI concerning the ability to efficiently improve the performance of a deep model over time, dealing with a long (and possibly unlimited) sequence of data/tasks. In this workshop, after a brief introduction of the subject, we’ll analyze different Continual Learning strategies and assess them on common Vision benchmarks. We’ll conclude the workshop with a look at possible real world application of CL.01:00 PM
by Bohdan Zhurakovskyi and Raid Arfua, language: ukr/rus
We will compare different clusterization models on images of soccer players, discuss which feature extraction techniques can be used for image preprocessing, and which metrics provide better clusterization results. We will see which neural networks is better to use for image embedding generation, and how to use those embeddings for player team clusterization and team incremental learning during the real football game.03:30 PM
by Oleksii Tsvietnov
We will discuss:
Datasets – size&quality, DataFactory
Creating project environment
Challenges in real data vs lab
Transition from RnD to Production
by Kyryl Truskovskyi, language: ukr/rus
We will discuss:
What are the generative adversarial networks?
What problems they can solve?
What is the good research project structure and how we do it in Neuromation?
We will do:
Train a small generative adversarial network
Train a simple classifier
Apply generative adversarial networks for a solving class imbalance problem06:00 PM
Join us, to be in the center of computer vision community, to share experience and chat with professionals.
We’re honoured to have amazing experts including Pedro Porto Buarque de Gusmão, Postdoctoral Researcher, at University of Oxford.
Lunch included. Afterparty with beer and good people is waiting for you!
For the workshops you only need to bring your laptop. Computational resources will be provided.
THE PRICE IS SYMBOLIC: 300uah.
If you have any questions about the event, please contact us directly.