On-device group equivariant CNNs
Traditional CNNs are not robust to certain symmetry transformations, such as rotation. Group-equivariant CNNs (G-CNNs) generalize well to a variety of transformations, including arbitrary rotations, but have been too complex to implement on a phone. Equivariant CNNs are compute efficient, data efficient, and offer robust performance. For the first time at NeurIPS 2020, we demonstrated G-CNNs running in real time on a phone. Our demo showcases how a G-CNN performs better than a traditional CNN on a segmentation mapping task to correctly classify each pixel of lymph node tissue scans as benign or malignant. Since tissue scans have no inherent orientation, we slowly rotate the images of the scans in 10-degree increments while running the segmentation task. The G-CNN provides a more accurate, stable, and robust classification.
https://www.qualcomm.com/research/art...