Lightweight Monocular Depth with a Novel Neural Architecture Search Method
This work addresses the need for efficient and compact depth estimation models, which is crucial for applications like robotics and autonomous driving, though it is incremental as it builds on existing NAS methods.
The paper tackles the problem of computationally expensive neural architecture search for lightweight monocular depth estimation by introducing LiDNAS, a novel method that uses Assisted Tabu Search and a pre-defined backbone to achieve superior performance and efficiency, with optimized models outperforming state-of-the-art compact models on datasets like NYU-Depth-v2, KITTI, and ScanNet while being 7%-500% more compact in size.
This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models. Unlike previous neural architecture search (NAS) approaches, where finding optimized networks are computationally highly demanding, the introduced novel Assisted Tabu Search leads to efficient architecture exploration. Moreover, we construct the search space on a pre-defined backbone network to balance layer diversity and search space size. The LiDNAS method outperforms the state-of-the-art NAS approach, proposed for disparity and depth estimation, in terms of search efficiency and output model performance. The LiDNAS optimized models achieve results superior to compact depth estimation state-of-the-art on NYU-Depth-v2, KITTI, and ScanNet, while being 7%-500% more compact in size, i.e the number of model parameters.