DeepAI AI Chat
Log In Sign Up

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

by   Lewei Yao, et al.

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? Neural architecture search (NAS) has shown great potential in finding an optimal solution. Existing NAS works for object detection only focus on searching better design of a single module such as backbone or feature fusion neck, while neglecting the balance of the whole system. In this paper, we present a two-stage coarse-to-fine searching strategy named Structural-to-Modular NAS (SM-NAS) for searching a GPU-friendly design of both an efficient combination of modules and better modular-level architecture for object detection. Specifically, Structural-level searching stage first aims to find an efficient combination of different modules; Modular-level searching stage then evolves each specific module and pushes the Pareto front forward to a faster task-specific network. We consider a multi-objective search where the search space covers many popular designs of detection methods. We directly search a detection backbone without pre-trained models or any proxy task by exploring a fast training from scratch strategy. The resulting architectures dominate state-of-the-art object detection systems in both inference time and accuracy and demonstrate the effectiveness on multiple detection datasets, e.g. halving the inference time with additional 1 mAP improvement compared to FPN and reaching 46 time of MaskRCNN.


page 1

page 2

page 3

page 4


LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds

Developing neural models that accurately understand objects in 3D point ...

EAutoDet: Efficient Architecture Search for Object Detection

Training CNN for detection is time-consuming due to the large dataset an...

Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation

Panoptic segmentation is posed as a new popular test-bed for the state-o...

CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending

We address the curve lane detection problem which poses more realistic c...

Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection

Recently, Neural Architecture Search has achieved great success in large...

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

Neural Architecture Search (NAS) has achieved great success in image cla...