CoChat

Mini-YOLOv3: Real-Time Object Detector for Embedded Applications

Open access
Mao, Qi-Chao, Sun, Hong-Mei, Liu, Yan-Bo, Jia, Rui-Sheng · 2019 · IEEE Access
Cited by 224

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Abstract

Real-time scene parsing through object detection running on an embedded device is very challenging, due to limited memory and computing power of embedded devices. To deal with these challenges, we redesign a lightweight network without notably reducing detection accuracy. Based on the Darknet-53, we use depth separable convolutions and pointwise group convolutions to reduce the parameter size of the network. A feature extraction backbone network with a parameter size of only 16 percent of darknet-53 is constructed. Meanwhile, in order to compensate for the degradation of accuracy, we have added a Multi-Scale Feature Pyramid Network based on a simple U-shaped structure to improve the performance of multi-scale object detection, which called it Mini-YOLOv3. It has smaller model size and fewer trainable parameters and floating point operations (FLOPs) in comparison of YOLOv3. We evaluate Mini-YOLOv3 on MS-COCO benchmark dataset; The parameter size of Mini-YOLOv3 is only 23% of YOLOv3 and achieves comparable detection accuracy as YOLOv3 but only requires 1/2 detect time, Specifically, Mini-YOLOv3 achieves mAP-50 of 52.1 at speed of 67 fps.

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/access.2019.2941547

Cites

27 of 27 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: 17

  1. dai, 2016, R-FCN: Object detection via region-based fully convolutional networks, Proc Adv Neural Inf Process Syst, 379
  2. 10.1109/ICPR.2006.479 · DOI · Paper page
  3. 10.1109/50.90937 · DOI · Paper page
  4. iandola, 2014, DenseNet: Implementing efficient convNet descriptor pyramids, Arxiv 1404 1869
  5. 10.1109/CVPR.2018.00109 · DOI · Paper page
  6. lin, 2014, Microsoft COCO: Common objects in context, Proc Eur Conf Comput Vis, 740
  7. 10.1109/CVPR.2014.81 · DOI · Paper page
  8. fridman, 2017, MIT advanced vehicle technology study: Large-scale naturalistic driving study of driver behavior and interaction with automation, arXiv 1711 06976
  9. 10.1109/SITIS.2016.17 · DOI
  10. iandola, 2016, SqueezeNet: AlexNet-level accuracy with $50\times$ fewer parameters and < 0.5 MB model size, arXiv 1602 07360
  11. 10.1109/CVPR.2001.990517 · DOI · Paper page
  12. wong, 2018, Tiny SSD: A tiny single-shot detection deep convolutional neural network for real-time embedded object detection, ArXiv 1802 06488
  13. 10.1006/cviu.1999.0830 · DOI · Paper page
  14. freund, 1996, Experiments with a new boosting algorithm, Proc 13th Int Conf Mach Learn, 148
  15. 10.1007/978-3-319-07488-7_8 · DOI
  16. 10.1109/CVPR.2008.4587597 · DOI · Paper page
  17. 10.1109/CVPR.2018.00719 · DOI · Paper page

Cited by

See all 224

Metadata

Authors
Mao, Q.-C., Sun, H.-M., Liu, Y.-B., & Jia, R.-S.
Venue
IEEE Access
Published
2019
Volume
7
Pages
133529-133538
ISSN
2169-3536 (ISSN-L)
OpenAlex
W2973696262
Cited by
224
References
27
FWCI
13.63
Type
journal article
Language
en
Open access
gold
Funders
  • Natural Science Foundation of Shandong Province (ZR2018MEE008)
  • Key Research and Development Program of Shandong Province, China (2017GSF20115)

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.