Fig. 8
From: Efficient attention vision transformers for monocular depth estimation on resource-limited hardware
Embedding dispersion is measured using entropy values, specifically differential Gaussian entropy (left plot) and Kozachenko-Leonenko entropy (right plot), where a lower value indicates a better encoder embedding distribution compactness. Results for each network on the KITTI dataset are grouped by model size: tiny (a), base (b), and large (c).
