Munich AI, Machine Learning and Computer Vision Meetup

In this talk, we’ll explore how to build self-improving computer vision systems through automated MLOps workflows. We’ll discuss how combining continuous data collection, automated retraining pipelines, and production feedback loops creates a “data flywheel” effect, where model performance improves organically through real-world usage.

Learn how to move beyond static models to systems that learn and adapt from production data, automatically identifying edge cases and performance gaps. We’ll examine practical strategies for implementing reproducible training pipelines, monitoring model drift, and leveraging active learning to optimize data collection efforts. Join us to discover how proper MLOps practices can transform your computer vision projects from one-off experiments into continuously evolving, production-grade systems that get better with every iteration.

Datasets are the lifeblood of machine learning, driving innovation and enabling breakthrough applications in computer vision and AI. This talk presents a curated exploration of the most compelling visual datasets unveiled at CVPR, ECCV, and NeurIPS 2024, with a unique twist – we’ll explore them live using FiftyOne, the open-source tool for dataset curation and analysis.

Using FiftyOne’s powerful visualization and analysis capabilities, we’ll take a deep dive into these collections, examining their unique characteristics through interactive sessions. We’ll demonstrate how to:

• Analyze dataset distributions and potential biases
• Identify edge cases and interesting samples
• Compare similar samples across datasets
• Explore multi-modal annotations and complex label structures

Whether you’re a researcher, practitioner, or dataset enthusiast, this session will provide hands-on insights into both the datasets shaping our field and practical tools for dataset exploration. Join us for a live demonstration of how modern dataset analysis tools can unlock deeper understanding of the data driving AI forward.