See Jan Jongboom and many other expert speakers at the 2023 Embedded Vision Summit!
Virtually all computer vision machine learning models involve classification—for example, “how many humans are in the frame?” To train such a model, you need examples of every class of object the model is intended to detect. But what happens when a new type of object appears? Ask a model trained only on elephants and zebras to classify a giraffe and it will happily misclassify the image. Similarly, when you train a model to detect flaws (like a broken bottle) on a production line, you need training data for every possible fault, which is impractical. The solution to this dilemma is FOMO-AD, an ML model for visual anomaly detection. FOMO-AD can be used along with classification models, in which case it flags cases where you shouldn’t trust the classifier (e.g., this animal is unlike anything I’ve ever seen), or it can be used standalone to detect anomalies without requiring the developer to define any explicit fault states.
Jan Jongboom is an embedded engineer and machine learning advocate, always looking for ways to gather more intelligence from the real world. He has shipped devices, worked on the latest network tech and simulated microcontrollers… and there’s a monument in San Francisco with his name on it. Currently, he serves as the co-founder and CTO of Edge Impulse, creator of the leading development platform for embedded machine learning. To date, 150,000+ projects have been developed using Edge Impulse.
Follow us on Twitter and LinkedIn.
Open for submissions! If you’re a start-up doing something cool with computer vision or visual AI, submit your entry today—for free! (Not at a computer vision or visual AI start-up but know one? Nominate them and you could win free Summit passes!) https://hubs.ly/Q01ws0cX0
Last chance! Don’t miss your chance to win year-round promotion of your company by the Alliance by winning an Edge AI and Vision Product of the Year Award. Submit your entry by December 31! https://hubs.ly/Q01svnzB0