CoChat

Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation

Open access
Zheng, Zhaohui, Wang, Ping, Ren, Dongwei, Liu, Wei, Ye, Rongguang, Hu, Qinghua, Zuo, Wangmeng · 2022 · IEEE Transactions on Cybernetics

The DOI matches its Crossref record; 57 of the 58 references it cites were found in a registry or an index, and 1 are not checked yet.

Abstract

Deep learning-based object detection and instance segmentation have achieved unprecedented progress. In this article, we propose complete-IoU (CIoU) loss and Cluster-NMS for enhancing geometric factors in both bounding-box regression and nonmaximum suppression (NMS), leading to notable gains of average precision (AP) and average recall (AR), without the sacrifice of inference efficiency. In particular, we consider three geometric factors, that is: 1) overlap area; 2) normalized central-point distance; and 3) aspect ratio, which are crucial for measuring bounding-box regression in object detection and instance segmentation. The three geometric factors are then incorporated into CIoU loss for better distinguishing difficult regression cases. The training of deep models using CIoU loss results in consistent AP and AR improvements in comparison to widely adopted$\ell _{n}$-norm loss and IoU-based loss. Furthermore, we propose Cluster-NMS, where NMS during inference is done by implicitly clustering detected boxes and usually requires fewer iterations. Cluster-NMS is very efficient due to its pure GPU implementation, and geometric factors can be incorporated to improve both AP and AR. In the experiments, CIoU loss and Cluster-NMS have been applied to state-of-the-art instance segmentation (e.g., YOLACT and BlendMask-RT), and object detection (e.g., YOLO v3, SSD, and Faster R-CNN) models. Taking YOLACT on MS COCO as an example, our method achieves performance gains as +1.7 AP and +6.2 AR100for object detection, and +1.1 AP and +3.5 AR100for instance segmentation, with 27.1 FPS on one NVIDIA GTX 1080Ti GPU. All the source code and trained models are available athttps://github.com/Zzh-tju/CIoU.

Overview

Integrity signals

Registry

Crossref · 10.1109/tcyb.2021.3095305

Cites

57 of 58 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 58 references

Research works printed but not linked: 1

  1. 10.1007/978–3-319-10602-148 · doi:10.1007/978-3-319-10602-148

Cited by

See all 1,552

Metadata

Authors
Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., & Zuo, W.
Affiliations
  • Tianjin University (CN)
  • Harbin Institute of Technology (CN)
Venue
IEEE Transactions on Cybernetics
Published
2022-08
Volume
52
Issue
8
Pages
8574-8586
ISSN
  • 2168-2267 (ISSN-L)
  • 2168-2275
OpenAlex
W3194790201
Cited by
1,552
References
52
Citations by year
2026: 239 · 2025: 466 · 2024: 475 · 2023: 242 · 2022: 102
FWCI
75.93
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Cybernetics (publishedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
National Natural Science Foundation of China (61801326, U19A2073)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
bounding box regression, non-maximum suppression, geometric factor, overlap area, aspect ratio, instance segmentation, object detection, YOLACT, inference efficiency
MeSH terms
Deep Learning

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: Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation. https://app.cochat.ai/papers/10.1109/tcyb.2021.3095305
The paper
Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., & Zuo, W. (2022). Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation. IEEE Transactions on Cybernetics. https://doi.org/10.1109/tcyb.2021.3095305

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.