Experience with Using Synthetic Training Images for Wearable Cognitive Assistance
March 2022 • Conference Paper
Roger Iyengar (Carnegie Mellon University), Emily Zhang (Carnegie Mellon University), Mahadev Satyanarayanan (Carnegie Mellon University)
This paper was presented at the 2022 AAAI Spring Symposium on AI Engineering.
Software Engineering Institute
Wearable Cognitive Assistance (WCA) applications use computer vision models that require thousands of labeled training images. Capturing and labeling these images requires a substantial amount of work. By using synthetically generated images for training, we avoided this labor-intensive step. The performance of these models was comparable to that of models that were trained on real images.