Poster

Self-Supervised AutoFlow

Hsin-Ping Huang · Charles Herrmann · Junhwa Hur · Erika Lu · Kyle Sargent · Austin Stone · Ming-Hsuan Yang · Deqing Sun

West Building Exhibit Halls ABC 303

Abstract:

Recently, AutoFlow has shown promising results on learning a training set for optical flow, but requires ground truth labels in the target domain to compute its search metric. Observing a strong correlation between the ground truth search metric and self-supervised losses, we introduce self-supervised AutoFlow to handle real-world videos without ground truth labels. Using self-supervised loss as the search metric, our self-supervised AutoFlow performs on par with AutoFlow on Sintel and KITTI where ground truth is available, and performs better on the real-world DAVIS dataset. We further explore using self-supervised AutoFlow in the (semi-)supervised setting and obtain competitive results against the state of the art.

Chat is not available.