Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two of its weaknesses: a large amount of rewritten labels and an inefficient distribution of anchors. Poly-YOLO reduces the issues by aggregating features from a light SE-Darknet-53 backbone with a hypercolumn technique, using stairstep upsampling, and produces a single scale output with high resolution. In comparison with YOLOv3, Poly-YOLO has only 60% of its trainable parameters but improves the mean average precision by a relative 40%. We also present Poly-YOLO lite with fewer parameters and a lower output resolution. It has the same precision as YOLOv3, but it is three times smaller and twice as fast, thus suitable for embedded devices. Finally, Poly-YOLO performs instance segmentation by bounding polygons. The network is trained to detect size-independent polygons defined on a polar grid. Vertices of each polygon are being predicted with their confidence, and therefore, Poly-YOLO produces polygons with a varying number of vertices. Source code is available at https://gitlab.com/irafm-ai/poly-yolo.
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.
Integrity signals
Registry
Cites
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.
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 2×
“We trained Poly-YOLO for 200 training and 100 validation images from Cityscapes dataset [32] for the version with direct upscaling and stairstep upscaling used in the hypercolumn.”
MethodSqueeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
YOLOv4: Optimal Speed and Accuracy of Object Detection
Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020) · arXiv · doi:10.48550/arxiv.2004.10934 · Cited by 10,307
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 2×
“We want to highlight that for feature extraction, an arbitrary SOTA backbone such as (SE)ResNeXt [12] or EfficientNet [10] can be used, which would probably increase the overall accuracy.”
MethodFCOS: Fully Convolutional One-Stage Object Detection
Tian, Z., Shen, C., Chen, H., & He, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00972 · Cited by 7,013
Cited by
Tang, Y., Zhou, H., Wang, H., & Zhang, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118573 · Cited by 258
OmniDet: Surround View Cameras Based Multi-Task Visual Perception Network for Autonomous Driving
Ravi Kumar, V., Yogamani, S., Rashed, H., Sitsu, G., Witt, C., Leang, I., Milz, S., & Mader, P. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062324 · Cited by 121
“The object contour can be uniformly sampled in the range of 360 ° split into N equal polygon vertices, each represented by the radial distance r from the object’s centroid as used in PolyYOLO [16].”
MethodAg-YOLO: A Real-Time Low-Cost Detector for Precise Spraying With Case Study of Palms
Qin, Z., Wang, W., Dammer, K.-H., Guo, L., & Cao, Z. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.753603 · Cited by 41
Metadata
- Authors
- Hurtik, P., Molek, V., Hula, J., Vajgl, M., Vlasanek, P., & Nejezchleba, T.
- Venue
- Neural Computing and Applications
- Published
- 2022-02-19
- Volume
- 34
- Issue
- 10
- Pages
- 8275-8290
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W3029960749
- Cited by
- 176
- References
- 19
- FWCI
- 11.41
- Type
- journal article
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3. https://app.cochat.ai/papers/10.1007/s00521-021-05978-9
- The paper
- Hurtik, P., Molek, V., Hula, J., Vajgl, M., Vlasanek, P., & Nejezchleba, T. (2022). Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3. Neural Computing and Applications. https://doi.org/10.1007/s00521-021-05978-9
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.