2019
DOI: 10.48550/arxiv.1911.09929
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

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

Abstract: 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 desig… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0

Year Published

2020
2020
2021
2021

Publication Types

Select...
7

Relationship

5
2

Authors

Journals

citations
Cited by 7 publications
(13 citation statements)
references
References 49 publications
0
13
0
Order By: Relevance
“…our searched detector based on R101 reaches 23.3 FPS and 43.9 AP, outperforming RepPoint-R101's 13.7 FPS and 41.0 AP by a large margin. Furthermore, our method (R101-based) surpasses most mainstream detection NAS methods (e.g., SM-NAS [42] and NAS-FPN [13]) and reaches comparable performance with the SOTA EfficientDet (D2) [37], while requiring much less search cost and no extra post-search training epochs.…”
Section: Comparison With State-of-the-artmentioning
confidence: 84%
See 2 more Smart Citations
“…our searched detector based on R101 reaches 23.3 FPS and 43.9 AP, outperforming RepPoint-R101's 13.7 FPS and 41.0 AP by a large margin. Furthermore, our method (R101-based) surpasses most mainstream detection NAS methods (e.g., SM-NAS [42] and NAS-FPN [13]) and reaches comparable performance with the SOTA EfficientDet (D2) [37], while requiring much less search cost and no extra post-search training epochs.…”
Section: Comparison With State-of-the-artmentioning
confidence: 84%
“…changes, which calls for a way of obtaining sufficient powerful teachers with low cost. The mainstream NAS approach [13,42,37] using a proxy task (e.g., training with fewer epochs) to train the teacher does not guarantee the quality of teacher's supervision. On the other hand, training every teacher detector from scratch is too costly.…”
Section: Mutate Teachermentioning
confidence: 99%
See 1 more Smart Citation
“…[30,6,33] propose to directly predict location of objects rather than based on anchor priors, which opens a new era for object detection. Recent works also perform NAS on detection tasks, which searches for novel detectors automatically without human intervention [13,32,10,34,35].…”
Section: Related Workmentioning
confidence: 99%
“…[27] seeks to bridge the gap between sample-based and one-shot approaches. Besides searching for an optimal cell design in earlier works [19], many recent works also investigate the macro skeleton search of a network [33,31].…”
Section: Introductionmentioning
confidence: 99%