DeepAI AI Chat
Log In Sign Up

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

by   Jianyuan Guo, et al.
HUAWEI Technologies Co., Ltd.
The University of Sydney
Peking University

Neural Architecture Search (NAS) has achieved great success in image classification task. Some recent works have managed to explore the automatic design of efficient backbone or feature fusion layer for object detection. However, these methods focus on searching only one certain component of object detector while leaving others manually designed. We identify the inconsistency between searched component and manually designed ones would withhold the detector of stronger performance. To this end, we propose a hierarchical trinity search framework to simultaneously discover efficient architectures for all components (i.e. backbone, neck, and head) of object detector in an end-to-end manner. In addition, we empirically reveal that different parts of the detector prefer different operators. Motivated by this, we employ a novel scheme to automatically screen different sub search spaces for different components so as to perform the end-to-end search for each component on the corresponding sub search space efficiently. Without bells and whistles, our searched architecture, namely Hit-Detector, achieves 41.4% mAP on COCO minival set with 27M parameters. Our implementation is available at


page 1

page 4

page 5

page 6

page 7

page 8

page 9

page 12


DetNAS: Neural Architecture Search on Object Detection

Object detectors are usually equipped with networks designed for image c...

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

The state-of-the-art object detection method is complicated with various...

FSD: Fully-Specialized Detector via Neural Architecture Search

In this paper, we first propose and examine a fully-automatic pipeline t...

Computation Reallocation for Object Detection

The allocation of computation resources in the backbone is a crucial iss...

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

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

MRF-UNets: Searching UNet with Markov Random Fields

UNet [27] is widely used in semantic segmentation due to its simplicity ...