DHAG-Net: A Small Object Semantic Segmentation Network Integrating Edge Supervision and Dense Hybrid Dilated Convolution
Source abstract
Abstract
Small-object semantic segmentation remains challenging in urban driving scenes due to limited pixel occupancy, blurred boundaries, and the constraints imposed by lightweight deployment. To address these issues, this paper presents a lightweight semantic segmentation framework that enhances boundary awareness and contextual representation while maintaining computational efficiency. The proposed method integrates an edge-supervised boundary gating module to emphasize object boundaries, an efficient multi-scale context aggregation strategy to mitigate scale variation, and a lightweight feature enhancement mechanism for effective feature fusion. Edge supervision is introduced as an auxiliary regularization signal and does not require additional manual annotations. Extensive experiments conducted on multiple benchmark datasets, including Cityscapes, CamVid, PASCAL VOC 2012, and IDDA, demonstrate that the proposed framework consistently improves segmentation performance, particularly for small-object categories, while preserving a favorable balance between accuracy and efficiency.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic Information, Guilin University of Electronic Technology, Guilin 541004, China
Funding
General Project of GuangXi Science and Technology Major Project
References (50)
Show source-provided references
1. Lu, Z., Li, J., Liu, Z., Cao, Q., Tian, T., Wang, X., and Huang, Z. (2025). Semi-Supervised Retinal Vessel Segmentation Based on Pseudo Label Filtering. Symmetry, 17.10.3390/sym17091462 ↗
2. Merging context clustering with visual state space models for medical image segmentation10.1109/TMI.2025.3525673 ↗
3. Orbe-Trujillo, E., Novillo, C.J., Pérez-Ramírez, M., Vazquez-Avila, J.L., and Pérez-Ramírez, A. (2022). Fast Treetops Counting Using Mathematical Image Symmetry, Segmentation, and Fast K-Means Classification Algorithms. Symmetry, 14.10.3390/sym14030532 ↗
4. Zhou, M., Hu, H.M., and Zhang, Y. (2014, January 9–12). Region-based intra-frame rate-control scheme for high efficiency video coding. Proceedings of the Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific, Siem Reap, Cambodia.10.1109/APSIPA.2014.7041648 ↗
5. Modified histogram-based segmentation and adaptive distance tracking of sperm cells image sequences10.1016/j.cmpb.2017.11.005 ↗
6. Long, J., Feng, X., Zhu, X., Zhang, J., and Gou, G. (2018). Efficient superpixel-guided interactive image segmentation based on graph theory. Symmetry, 10.10.3390/sym10050169 ↗
7. Graph-represented distribution similarity index for full-reference image quality assessment10.1109/TIP.2024.3390565 ↗
8. Dey, N., Rajinikanth, V., Ashour, A.S., and Tavares, J.M.R. (2018). Social group optimization supported segmentation and evaluation of skin melanoma images. Symmetry, 10.10.3390/sym10020051 ↗
9. LSRL-Net: A level set-guided re-learning network for semi-supervised cardiac and prostate segmentation10.1016/j.bspc.2025.108062 ↗
10. Learning efficient and effective trajectories for differential equation-based image restoration10.1109/TPAMI.2025.3584921 ↗
11. Hasan, A.M., Meziane, F., Aspin, R., and Jalab, H.A. (2016). Segmentation of brain tumors in MRI images using three-dimensional active contour without edge. Symmetry, 8.10.3390/sym8110132 ↗
12. Robust edge-stop functions for edge-based active contour models in medical image segmentation10.1109/LSP.2015.2508039 ↗
13. An ADMM approach to masked signal decomposition using subspace representation10.1109/TIP.2019.2894966 ↗
14. Low-light image enhancement via a frequency-based model with structure and texture decomposition10.1145/3590965 ↗
15. Hu, H., Fang, B., Duo, B., Wei, X., Yan, J., Xian, W., and Li, D. (2025). A Symmetric Multiscale Detail-Guided Attention Network for Cardiac MR Image Semantic Segmentation. Symmetry, 17.10.3390/sym17111807 ↗
16. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
17. ImageNet Classification with Deep Convolutional Neural Networks10.1145/3065386 ↗
18. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very deep convolutional networks for large-scale image recognition. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), San Diego, CA, USA.
19. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going Deeper with Convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
20. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
21. Fully Convolutional Networks for Semantic Segmentation
22. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation, Springer.10.1007/978-3-319-24574-4_28 ↗
23. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation10.1109/TPAMI.2016.2644615 ↗
24. Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2014). Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv.
25. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs10.1109/TPAMI.2017.2699184 ↗
26. Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv.
27. Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, Springer.10.1007/978-3-030-01234-2_49 ↗
28. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3–7). An Image is Worth 16 × 16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations, Virtual.
29. Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., and Luo, P. (2021). SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. arXiv.
30. Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., and Girdhar, R. (2022, January 19–24). Masked-attention Mask Transformer for Universal Image Segmentation. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orlean, LA, USA.10.1109/CVPR52688.2022.00135 ↗
31. ABANet: Attention boundary-aware network for image segmentation10.1111/exsy.13625 ↗
32. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature Pyramid Networks for Object Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
33. Sun, K., Xiao, B., Liu, D., and Wang, J. (2019, January 15–20). Deep High-Resolution Representation Learning for Human Pose Estimation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00584 ↗
34. An improved DeepLabv3+ lightweight network for remote-sensing image semantic seg-mentation10.1007/s40747-023-01304-z ↗
35. Wang, Y., Song, J., Wang, S., Zhang, Y., He, P., and Yang, C. (2023). Surface-Framework structure: A neural network structure for weakening gridding effect in PCB mark-point semantic segmentation. PLoS ONE, 18.10.1371/journal.pone.0283809 ↗
36. Hybrid dilated convolution guided feature filtering and enhancement strategy for hyperspectral image classification
37. Li, Z., Lyu, H., and Wang, J. (2024, January 5–8). FusionU-Net: U-Net with Enhanced Skip Connection for Pathology Image Segmentation. Proceedings of the Asian Conference on Machine Learning, Hanoi, Vietnam.
38. Peng, Y., Sonka, M., and Chen, D.Z. (2025, January 14–17). U-Net V2: Rethinking the Skip Connections of U-Net for Medical Image Segmentation. Proceedings of the 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), Houston, TX, USA.10.1109/ISBI60581.2025.10980742 ↗
39. CAT-Unet: An enhanced U-Net architecture with coordinate attention and skip-neighborhood attention transformer for medical image segmentation10.1016/j.ins.2024.120578 ↗
40. Sawant, S.S., Medgyesy, A., Raghunandan, S., and Götz, T. (2025, January 23–25). LMSC-UNet: A Lightweight U-Net with Modified Skip Connections for Semantic Seg-mentation. Proceedings of the 17th International Conference on Agents and Artificial Intelligence, Porto, Portugal.10.5220/0013343800003890 ↗
41. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
42. Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016, January 27–30). The Cityscapes Dataset for Semantic Urban Scene Understanding. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.350 ↗
43. Brostow, G.J., Shotton, J., Fauqueur, J., and Cipolla, R. (2008, January 12–18). Segmentation and Recognition Using Structure from Motion Point Clouds. Proceedings of the European Conference on Computer Vision, Marseille, France.10.1007/978-3-540-88682-2_5 ↗
44. The Pascal Visual Object Classes Challenge: A Retrospective10.1007/s11263-014-0733-5 ↗
45. IDDA: A Large-Scale Multi-Domain Dataset for Autonomous Driving10.1109/LRA.2020.3009075 ↗
46. Zhang, J., and Chen, N. (2025). Bidirectional Dynamic Adaptation: Mutual Learning with Cross-Network Feature Rectification for Urban Segmentation. Appl. Sci., 15.10.3390/app151810000 ↗
47. Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation10.1007/s11263-021-01515-2 ↗
48. Haformer: Unleashing the power of hierarchy-aware features for lightweight semantic segmentation10.1109/TIP.2024.3425048 ↗
49. Wan, Z., Zhang, P., Wang, Y., Yong, S., Stepputtis, S., Sycara, K., and Xie, Y. (March, January 6). Sigma: Siamese mamba network for multi-modal semantic segmentation. Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA.10.1109/WACV61041.2025.00176 ↗
50. Chen, L., Lin, G., and Ying, F. (2024). When semantic segmentation meets frequency aliasing. arXiv.