Parameter search-based scaling network for self-supervised depth

Abstract

The selection of the benchmark network in self-supervised monocular depth-based estimation can often only be made using previous networks to select the best performers among them. When there is a change in resources and want to scale the network, it is difficult to find a suitable way to adjust the network quickly if the selected network itself does not give the same series of networks of different sizes. In this paper, we investigate whether the network generated by the Neural Architecture Search method based on search parameter scaling has good robustness in monocular depth estimation based self-supervised, as which the pose estimation network as well as the depth estimation network can have a better improvement in the accuracy of depth estimation. The final experiments show that the generated series perform well on the KITTI dataset, with the best performing EfficientNet-B3 outperforming all previous self-supervised networks.