CoChat

Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images

Open access

The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.

Abstract

In recent years, ship detection in satellite remote sensing images has become an important research topic. Most existing methods detect ships by using a rectangular bounding box but do not perform segmentation down to the pixel level. This paper proposes a ship detection and segmentation method based on an improved Mask R-CNN model. Our proposed method can accurately detect and segment ships at the pixel level. By adding a bottom-up structure to the FPN structure of Mask R-CNN, the path between the lower layers and the topmost layer is shortened, allowing the lower layer features to be more effectively utilized at the top layer. In the bottom-up structure, we use channel-wise attention to assign weights in each channel and use the spatial attention mechanism to assign a corresponding weight at each pixel in the feature maps. This allows the feature maps to respond better to the target’s features. Using our method, the detection and segmentation mAPs increased from 70.6% and 62.0% to 76.1% and 65.8%, respectively.

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.2020.2964540

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Figures

FIGURE 1 Detection and segmentation results using our model. (a) Sea area 1, (b) sea area 2, (c) harbor area.
FIGURE 1 Detection and segmentation results using our model. (a) Sea area 1, (b) sea area 2, (c) harbor area.CC-BY · From the PDF
FIGURE 2 Illustration of the network: the B-CA-SA module represents the bottom-up structure with channel-wise and spatial attention mechanisms.
FIGURE 2 Illustration of the network: the B-CA-SA module represents the bottom-up structure with channel-wise and spatial attention mechanisms.CC-BY · From the PDF
FIGURE 3 FPN with bottom-up path structure from N 2 to N 5 . On the left is FPN structure without any changes.
FIGURE 3 FPN with bottom-up path structure from N 2 to N 5 . On the left is FPN structure without any changes.CC-BY · From the PDF
FIGURE 4 Sample features in different channels.
FIGURE 4 Sample features in different channels.CC-BY · From the PDF
FIGURE 5 Illustration of Channel-wise Attention (CA) and Spatial Attention (SA).
FIGURE 5 Illustration of Channel-wise Attention (CA) and Spatial Attention (SA).CC-BY · From the PDF
FIGURE 6 (a) FPN with attention module. (b) Bottom-up structure with attention module. Four different types of Attention Modules (AM): Channel-wise Attention (CA) Module, Spatial Attention (SA) Module, SA-CA module (combination of SA and CA modules), and CA-SA module (combination of CA and SA modules).
FIGURE 6 (a) FPN with attention module. (b) Bottom-up structure with attention module. Four different types of Attention Modules (AM): Channel-wise Attention (CA) Module, Spatial Attention (SA) Module, SA-CA module (combination of SA and CA modules), and CA-SA module (combination of CA and SA modules).CC-BY · From the PDF
FIGURE 7 (a) Illustration of the building blocks of FPN-AM. (b) Illustration of the building blocks of B-AM.
FIGURE 7 (a) Illustration of the building blocks of FPN-AM. (b) Illustration of the building blocks of B-AM.CC-BY · From the PDF
FIGURE 8 Translation of annotation format: (a) original image, (b) ground truths in RLE format, (c) ground truths in COCO annotation format, (d) ground truths in horizontal bounding box format, (e) ground truths in oriented bounding box format.
FIGURE 8 Translation of annotation format: (a) original image, (b) ground truths in RLE format, (c) ground truths in COCO annotation format, (d) ground truths in horizontal bounding box format, (e) ground truths in oriented bounding box format.CC-BY · From the PDF
FIGURE 9 Samples of ships detection and segmentation: (a) original images, (b) ground truths, (c) results from Mask R-CNN baseline model, (d) results from Mask R-CNN [44], (e) results from Mask Scoring R-CNN model, (f) results from PANet model, (g) results from SCRDet model, (h) results from Mask R-CNN_B-CA-SA (ours). Ships in the ground truths and objects detected by the models are circled in red.
FIGURE 9 Samples of ships detection and segmentation: (a) original images, (b) ground truths, (c) results from Mask R-CNN baseline model, (d) results from Mask R-CNN [44], (e) results from Mask Scoring R-CNN model, (f) results from PANet model, (g) results from SCRDet model, (h) results from Mask R-CNN_B-CA-SA (ours). Ships in the ground truths and objects detected by the models are circled in red.CC-BY · From the PDF
Image 10
CC-BY · From the PDF
Image 11
CC-BY · From the PDF
Image 12
CC-BY · From the PDF
Image 13
CC-BY · From the PDF
Image 14
CC-BY · From the PDF

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

Show all 49 references

Research works printed but not linked: 2

  1. 2019, Airbus Ship Detection Challenge
  2. massa, 2018, Maskrcnn-Benchmark Fast Modular Reference Implementation of Instance Segmentation and Object Detection Algorithms in Pytorch

Cited by

See all 204

Metadata

Authors
Nie, X., Duan, M., Ding, H., Hu, B., & Wong, E. K.
Affiliations
  • Northwestern Polytechnical University (CN)
  • Chinese Academy of Sciences (CN)
  • New York University (US)
Venue
IEEE Access
Published
2020
Volume
8
Pages
9325-9334
ISSN
2169-3536 (ISSN-L)
OpenAlex
W3000097815
Cited by
200
References
49
Citations by year
2026: 10 · 2025: 36 · 2024: 38 · 2023: 40 · 2022: 38 · 2021: 22 · 2020: 16
FWCI
11.27
Type
journal article
Language
en
Open access
Locations
  • IEEE Access (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Institutional Repository of Xi'an Institute of Optics and Fine Mechanics, Chinese Academy of Sciences (Xian Institute of Optics and Precision Mechanics) (submittedVersion, cc-by-nc-sa)
Funders
  • 2018 Science and Technology Plan of Shaanxi Province (2018ZDXM-GY-108)
  • Chinese Academy of Sciences (LSIT201706D)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
ship detection, ship segmentation, Mask R-CNN, satellite imagery, channel attention, spatial attention, feature pyramid network, pixel-level segmentation

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: Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images. https://app.cochat.ai/papers/10.1109/access.2020.2964540
The paper
Nie, X., Duan, M., Ding, H., Hu, B., & Wong, E. K. (2020). Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images. IEEE Access. https://doi.org/10.1109/access.2020.2964540

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.