CoChat

MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices

Open access
Chen, Bo, Ghiasi, Golnaz, Liu, Hanxiao, Lin, Tsung-Yi, Kalenichenko, Dmitry, Adam, Hartwig, Le, Quoc V. · 2020 · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 58

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

Abstract

Despite the blooming success of architecture search for vision tasks in resource-constrained environments, the design of on-device object detection architectures have mostly been manual. The few automated search efforts are either centered around non-mobile-friendly search spaces or not guided by on-device latency. We propose MnasFPN, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models. The learned MnasFPN head, when paired with MobileNetV2 body, outperforms MobileNetV3+SSDLite by 1.8 mAP at similar latency on Pixel. It is both 1 mAP more accurate and 10\% faster than NAS-FPNLite. Ablation studies show that the majority of the performance gain comes from innovations in the search space. Further explorations reveal an interesting coupling between the search space design and the search algorithm, for which the complexity of MnasFPN search space is opportune.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr42600.2020.01362

Cites

18 of 18 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 16

  1. zhang, 2018, Shufflenet: An extremely efficient convolutional neural network for mobile devices, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6848
  2. 10.1109/ICCV.2019.00137 · DOI · Paper page
  3. hu, 2018, Squeeze-and-excitation networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7132
  4. li, 2019, Random search and reproducibility for neural architecture search
  5. 10.1109/CVPR.2019.00017 · DOI · Paper page
  6. liu, 0, Ssd: Single shot multibox detector, European Conference on Computer Vision, 21
  7. loshchilov, 2016, SGDR Stochastic gradient descent with warm restarts
  8. hieu, 2018, Efficient Neural Architecture Search via Parameter Sharing
  9. qin, 2019, Thundernet Towards real-time generic object detection
  10. 10.1109/CVPR.2019.01099 · DOI · Paper page
  11. chen, 2019, DetNAS Neural Architecture Search on Object Detection
  12. robert, 2018, Pelee: A real-time object detection system on mobile devices, Advances in neural information processing systems, 1963
  13. dai, 2016, R-fcn: Object detection via region-based fully convolutional networks, Advances in neural information processing systems, 379
  14. bender, 2018, Understanding and simplifying one-shot architecture search, International Conference on Machine Learning, 549
  15. 10.1109/CVPR.2018.00474 · DOI · Paper page
  16. tan, 2019, Efficientnet Rethinking model scaling for convolutional neural networks

Cited by

See all 58

Metadata

Authors
Chen, B., Ghiasi, G., Liu, H., Lin, T.-Y., Kalenichenko, D., Adam, H., & Le, Q. V.
Venue
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2020-06
Pages
13604-13613
ISSN
1063-6919 (ISSN-L)
OpenAlex
W3034326778
Cited by
58
References
18
FWCI
3.16
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.