Paul Endresen, CEO of 3LC, demonstrates the company’s latest edge AI and vision technologies and products at the 2025 Embedded Vision Summit. Specifically, Andresen demonstrates how to uncover hidden treasures in the COCO dataset – like unlabeled forks and phantom objects – using his platform’s training-time introspection tools.
In this demo, 3LC eavesdrops on a YOLO model as it learns, surfacing high-confidence false positives that hint at mislabeled or missing data. Andresen cleans house with a few clicks, adds 11,229 new masks, and retrains for a better model – no annotation headaches required. It’s like debugging your dataset…while your model trains itself.
