Dynamic YOLO for small underwater object detection
Open accessAbstract
Abstract The practical application of object detection inevitably encounters challenges posed by small objects. In underwater object detection, a crucial method for marine exploration, the presence of small objects in underwater environments significantly hampers the performance of detection. In this paper, a dynamic YOLO detector is proposed as a solution to alleviate this problem. Specifically, a light-weight backbone network is first constructed based on deformable convolution v3, with some specialized designs for small object detection. Secondly, a unified feature fusion framework based on channel-wise, scale-wise, and spatial-aware attention is proposed to fuse feature maps from different scales. This is particularly critical for detecting small objects since it allows us to fully exploit the enhanced capabilities offered by our proposed backbone network. Finally, a simple but effective detection head is designed to handle the conflict between classification and localization by disentangling and aligning the two tasks. Extensive experiments are conducted on benchmark datasets to demonstrate the effectiveness of the proposed model. Without bells and whistles, dynamic YOLO outperforms the recent state-of-the-art methods by a large margin of $$+\,0.8$$ + 0.8 AP and $$+\,1.8$$ + 1.8 $$\text {AP}_{S}$$ AP S on the DUO dataset. Experimental results on Pascal VOC and MS COCO datasets also demonstrate the superiority of the proposed method. At last, ablation studies are conducted on DUO dataset to validate the effectiveness and efficiency of each design in dynamic YOLO. Source code will be available at https://github.com/chenjie04/Dynamic-YOLO .
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Dynamic detection models allow YOLO to adapt to evolving criteria in real-time scenarios.
“Another advancement is the development of dynamic detection models, which allow YOLO to adapt to evolving criteria in real-time scenarios [148].”
From The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection (2024) · cites this paper as [148]
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 56,035 · see citing works
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939 · cited 3× · see citing works
“Several representative one-stage (Li et al. 2020; Lin et al. 2017b; Tian et al. 2019; Zhang et al. 2020) and multi-stage detectors (Cai and Vasconcelos 2018; Ren et al. 2015; Yang et al. 2019) are adopted for comparison.”
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022) · arXiv · doi:10.48550/arxiv.2207.02696 · Cited by 13,205 · see citing works
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00721 · Cited by 13,198 · see citing works
EfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 2× · see citing works
“In order to establish a simple and efficient multi-scale feature fusion network, BiFPN (Tan et al. 2020) eliminates redundant nodes while extensively incorporating skip-connections to enhance output representation, achieving a better trade-off between accuracy and efficiency.”
Deformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · see citing works
Cascade R-CNN: Delving Into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00644 · Cited by 7,370 · see citing works
FCOS: 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 · see citing works
Jocher, G., Stoken, A., Borovec, J., NanoCode012, ChristopherSTAN, Changyu, L., Laughing, Hogan, A., Lorenzomammana, Tkianai, et al. (2020) · Zenodo · doi:10.5281/zenodo.3983579 · Cited by 2,738 · see citing works
Attention mechanisms in computer vision: A survey
Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R. R., Cheng, M.-M., & Hu, S.-M. (2022) · Computational Visual Media · doi:10.1007/s41095-022-0271-y · Cited by 2,566 · cited 2× · see citing works
“Spatial-aware attention enhances representation capabilities by selectively focusing on crucial regions of the feature map and suppressing unnecessary context, enabling precise feature extraction for object detection (Guo et al. 2022).”
InfluentialTOOD: Task-aligned One-stage Object Detection
Feng, C., Zhong, Y., Gao, Y., Scott, M. R., & Huang, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00349 · Cited by 1,668 · cited 2× · see citing works
“The conflict between classification and localization tasks has long been acknowledged in the field of object detection (Feng et al. 2021; Ge et al. 2021; Song et al. 2020; Wu et al. 2020).”
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01385 · Cited by 1,080 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Ali, M. L., & Zhang, Z. (2024) · Computers · doi:10.3390/computers13120336 · Cited by 383 · see citing works
- Authors
- Chen, J., & Er, M. J.
- Affiliations
- Dalian Maritime University (CN)
- Corresponding author
- Er, Meng Joo
- Venue
- Artificial Intelligence Review
- Published
- 2024-06-06
- Volume
- 57
- Issue
- 7
- ISSN
- 0269-2821 (ISSN-L)
- 1573-7462
- OpenAlex
- W4399384347
- Cited by
- 110
- References
- 12
- Citations by year
- 2026: 60 · 2025: 44 · 2024: 6
- FWCI
- 15.47
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Artificial Intelligence Review (publishedVersion, cc-by)
- Funders
- Fundamental Research Funds for the Central Universities (3132019344)
- Leading Scholar Grant, Dalian Maritime University (00253007)
- 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
- underwater object detection, small object detection, YOLO, deformable convolution, lightweight backbone, multi-scale feature fusion, attention mechanism, ocean exploration
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
