Papers › SP-NAS: Serial-to-Parallel Backbone Search for Object Detection

SP-NAS: Serial-to-Parallel Backbone Search for Object Detection

1 Jun 2020CVPR 2020 6archive 2025-07-28

Chenhan Jiang, Hang Xu, Wei Zhang, Xiaodan Liang, Zhenguo Li

Advanced object detectors usually adopt a backbone network designed and pretrained by ImageNet classification. Recently neural architecture search (NAS) has emerged to automatically design a task-specific backbone to bridge the gap between the tasks of classification and detection. In this paper, we propose a two-phase serial-to-parallel architecture search framework named SP-NAS towards a flexible task-oriented detection backbone. Specifically, the serial-searching round aims at finding a sequence of serial blocks with optimal scale and output channels in the feature hierarchy by a Swap-Expand-Reignite search algorithm; the parallel-searching phase then assembles several sub-architectures along with the previous searched backbone into a more powerful parallel-structured backbone. We efficiently search a detection backbone by exploring a network morphism strategy on multiple detection benchmarks. The resulting architectures achieve SOTA results, i.e. top performance (LAMR: 0.055) on the automotive detection leaderboard of EuroCityPersons benchmark, improving 2.3% mAP with less FLOPS than NAS-FPN on COCO, and reaching 84.1% AP50 on VOC better than DetNAS and Auto-FPN in terms of both accuracy and speed.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

2023-MindSpore-4/Code11 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code14 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code7 mindsporeSyntology: not harvested report
Mind23-2/MindCode-88 mindsporeSyntology: not harvested report
code-implementation1/Code8 mindsporeSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationNeural Architecture SearchObject Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Average PoolingBatch NormalizationConvolutionDetNASGlobal Average PoolingLSTMNAS-FPNReLUSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections