Date: Wednesday, May 21
Start Time: 4:15 pm
End Time: 4:45 pm
When developing computer vision-based products, getting from a proof of concept to a robust product ready for deployment can be a massive undertaking. The most vexing challenges in this process often relate to the “long-tail problem,” which arises when datasets have highly imbalanced distributions of classes. In this interview with Chris Padwick, we’ll delve into lessons learned from Chris’s years of experience developing automated farming equipment for deployment at scale and explore practical strategies for data curation, data labeling and model testing approaches. We’ll also discuss approaches for tackling challenges such as object class confusion and correlated training data. Bring your questions and join us for a candid conversation on the realities of delivering reliable computer vision products to market.
