SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

22 Nov 2019Lewei YaoHang XuWei ZhangXiaodan LiangZhenguo Li

The state-of-the-art object detection method is complicated with various modules such as backbone, feature fusion neck, RPN and RCNN head, where each module may have different designs and structures. How to leverage the computational cost and accuracy trade-off for the structural combination as well as the modular selection of multiple modules?.. (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper