EGSNet: An Efficient Glass Segmentation Network Based on Multi-Level Heterogeneous Architecture and Boundary Awareness
Source abstract
Abstract
Existing glass segmentation networks have high computational complexity and large memory occupation, leading to high hardware requirements and time overheads for model inference, which is not conducive to efficiency-seeking r... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Retinal Imaging and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (43)
Show source-provided references
1. Don’t hit me glass detection in real-world scenes
2. NeRF-Det: Learning geometry-aware volumetric representation for multi-view 3D object detection
3. MonoScene: Monocular 3D semantic scene completion
4. TOM-Net: Learning transparent object matting from a single image
5. TROSD: A new rgb-d dataset for transparent and reflective object segmentation in practice10.1109/TCSVT.2023.3254665 ↗
6. Segmenting transparent objects in the wild
7. Segmenting transparent objects in the wild with transformer
8. Large-field contextual feature learning for glass detection
9. Rich context aggregation with reflection prior for glass surface detection
10. Multi-view dynamic reflection prior for video glass surface detection
11. Progressive glass segmentation10.1109/TIP.2022.3162709 ↗
12. Glass segmentation using intensity and spectral polarization cues
13. Glass segmentation with RGB-thermal image pairs10.1109/TIP.2023.3256762 ↗
14. Enhanced boundary learning for glass-like object segmentation
15. Exploiting semantic relations for glass surface detection
16. DCNet: Glass-like object detection via detail-guided and cross-level Fusion
17. Glass makes blurs: Learning the visual blurriness for glass surface detection10.1109/TII.2024.3352232 ↗
18. Glass surface detection method based on visual distortion
19. C. Zheng, P. Li, X. Zhang, X. Lu, and M. Wei, “Don’t worry about mistakes! glass segmentation network via mistake correction,” 2023, arXiv:2304.10825.
20. X. Qin, J. Liu, Q. Wang, S. Zhang, F. Zhu and Z. Yi, “Fourier boundary features network with wider catchers for glass segmentation,” 2024, arXiv:2405.09459.
21. RefineNet: Multi-path refinement networks for high-resolution semantic segmentation
22. Encoder-decoder with atrous separable convolution for semantic image segmentation
23. Y. Cao, Z. Zhang, and E. Xie, “Fakemix augmentation improves transparent object detection,” 2021, arXiv:2103.13279.
24. Subgroups for detection transformer
25. Infrared and visible image fusion based on Res2Net-transformer automatic encoding and decoding
26. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers
27. Where is my mirror?
28. Progressive mirror detection
29. Symmetry-aware transformer-based mirror detection
30. Efficient mirror detection via multi-level heterogeneous learning
31. Aggregated residual transformations for deep neural networks
32. C. -Y. Wang, I. H. Yeh, and H. -Y. M. Liao, “YOLOv9: Learning what you want to learn using programmable gradient information,” 2024, arXiv:2402.13616.10.1007/978-3-031-72751-1_1 ↗
33. Xception: Deep learning with depthwise separable convolutions
34. Coordinate attention for efficient mobile network design
35. TP-MobNet: A two-pass mobile network for low-complexity classification of acoustic scene
36. DenseASPP for semantic segmentation in street scenes
37. CrossFormer embedding deeplabv3+ for remote sensing images semantic segmentation
38. Squeeze-and-Excitation Networks
39. UrbanEvolver: Function-aware urban layout regeneration10.1007/s11263-024-02030-w ↗
40. Wei · 2020 · 12321
41. Camouflaged object detection with feature decomposition and edge reconstruction
42. Looking at boundary: Siamese densely cooperative fusion for salient object detection10.1109/TNNLS.2021.3113657 ↗
43. Pyramid scene parsing network