Why Does Data-Driven Beat Theory-Driven Computer Vision?

This paper proposes that despite the success of deep learning methods in computer vision, the dominance we see would not have been possible by the methods of deep learning alone: the tacit change has been the evolution of empirical practice in computer vision. We demonstrate this by examining the distribution of sensor settings in vision datasets, only one potential dataset bias, and performance of both classic and deep learning algorithms under various camera settings. This reveals a strong mismatch between optimal performance ranges of theory-driven algorithms and sensor setting distributions in common vision datasets.