Fast Neural Architecture Search for Lightweight Dense Prediction Networks [article]

Lam Huynh, Esa Rahtu, Jiri Matas, Janne Heikkila
2022 arXiv   pre-print
We present LDP, a lightweight dense prediction neural architecture search (NAS) framework. Starting from a pre-defined generic backbone, LDP applies the novel Assisted Tabu Search for efficient architecture exploration. LDP is fast and suitable for various dense estimation problems, unlike previous NAS methods that are either computational demanding or deployed only for a single subtask. The performance of LPD is evaluated on monocular depth estimation, semantic segmentation, and image
more » ... olution tasks on diverse datasets, including NYU-Depth-v2, KITTI, Cityscapes, COCO-stuff, DIV2K, Set5, Set14, BSD100, Urban100. Experiments show that the proposed framework yields consistent improvements on all tested dense prediction tasks, while being 5%-315% more compact in terms of the number of model parameters than prior arts.
arXiv:2203.01994v3 fatcat:nnz34pody5banfrqpkaanpszau