Papers
Topics
Authors
Recent
Search
2000 character limit reached

LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation

Published 17 Mar 2024 in cs.CV | (2403.11122v1)

Abstract: Few-shot segmentation models excel in metal defect detection due to their rapid generalization ability to new classes and pixel-level segmentation, rendering them ideal for addressing data scarcity issues and achieving refined object delineation in industrial applications. Existing works neglect the \textit{Intra-Class Differences}, inherent in metal surface defect data, which hinders the model from learning sufficient knowledge from the support set to guide the query set segmentation. Specifically, it can be categorized into two types: the \textit{Semantic Difference} induced by internal factors in metal samples and the \textit{Distortion Difference} caused by external factors of surroundings. To address these differences, we introduce a \textbf{L}ocal d\textbf{E}scriptor based \textbf{R}easoning and \textbf{E}xcitation \textbf{Net}work (\textbf{LERENet}) to learn the two-view guidance, i.e., local and global information from the graph and feature space, and fuse them to segment precisely. Since the relation structure of local features embedded in graph space will help to eliminate \textit{Semantic Difference}, we employ Multi-Prototype Reasoning (MPR) module, extracting local descriptors based prototypes and analyzing local-view feature relevance in support-query pairs. Besides, due to the global information that will assist in countering the \textit{Distortion Difference} in observations, we utilize Multi-Prototype Excitation (MPE) module to capture the global-view relations in support-query pairs. Finally, we employ an Information Fusion Module (IFM) to fuse learned prototypes in local and global views to generate pixel-level masks. Our comprehensive experiments on defect datasets demonstrate that it outperforms existing benchmarks, establishing a new state-of-the-art.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Triplet-graph reasoning network for few-shot metal generic surface defect segmentation. IEEE Transactions on Instrumentation and Measurement, 70:1–11, 2021.
  2. Few-shot rotation-invariant aerial image semantic segmentation. IEEE Transactions on Geoscience and Remote Sensing, 62:1–13, 2023.
  3. Few-shot rotation-invariant aerial image semantic segmentation. IEEE Transactions on Geoscience and Remote Sensing, 62:1–13, 2024.
  4. Graph-based global reasoning networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 433–442, 2019.
  5. Apanet: Adaptive prototypes alignment network for few-shot semantic segmentation. IEEE Transactions on Multimedia, 25:4361–4373, 2022.
  6. Self-regularized prototypical network for few-shot semantic segmentation. Pattern Recognition, 133:109018, 2023.
  7. Detection mature bud for daylily based on faster r-cnn integrated with cbam. IEEE Access, 11:81646–81655, 2023.
  8. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning, pages 1126–1135, 2017.
  9. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016.
  10. An end-to-end steel surface defect detection approach via fusing multiple hierarchical features. IEEE Transactions on Instrumentation and Measurement, 69(4):1493–1504, 2020.
  11. Learning foreground information bottleneck for few-shot semantic segmentation. Pattern Recognition, 146:109993, 2024.
  12. Local descriptor-based multi-prototype network for few-shot learning. Pattern Recognition, 116:107935, 2021.
  13. Learning what not to segment: A new perspective on few-shot segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8057–8067, 2022.
  14. Beyond the prototype: divide-and-conquer proxies for few-shot segmentation. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, pages 1024–1030, 2022.
  15. Revisiting local descriptor based image-to-class measure for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7260–7268, 2019.
  16. Distribution consistency based covariance metric networks for few-shot learning. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, pages 8642–8649, 2019.
  17. Adaptive prototype learning and allocation for few-shot segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8334–8343, 2021.
  18. Dual prototype learning for few shot semantic segmentation. IEEE Access, 12:6356–6364, 2024.
  19. Semantic segmentation of remote sensing images by interactive representation refinement and geometric prior-guided inference. IEEE Transactions on Geoscience and Remote Sensing, 62:1–18, 2024.
  20. Few-shot semantic segmentation with support-induced graph convolutional network. In Proceedings of the British Machine Vision Conference 2022, pages 1–14, 2022.
  21. Axial assembled correspondence network for few-shot semantic segmentation. IEEE/CAA Journal of Automatica Sinica, 10(3):711–721, 2023.
  22. Automated visual defect detection for flat steel surface: A survey. IEEE Transactions on Instrumentation and Measurement, 69(3):626–644, 2020.
  23. Graph fairing convolutional networks for anomaly detection. Pattern Recognition, 145:109960, 2024.
  24. Defect classification with svm and wideband excitation in multilayer aluminum plates. IEEE Transactions on Instrumentation and Measurement, 69(1):241–248, 2019.
  25. Hierarchical dense correlation distillation for few-shot segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 23641–23651, 2023.
  26. One-shot learning for semantic segmentation. In Proceedings of the British Machine Vision Conference 2017, pages 1–13, 2017.
  27. The amalgamation of the object detection and semantic segmentation for steel surface defect detection. Applied Sciences, 12(12):6004, 2022.
  28. Faster rcnn target detection algorithm integrating cbam and fpn. Applied Sciences, 13(12):6913, 2023.
  29. Very deep convolutional networks for large-scale image recognition. In Proceedings of the 3rd International Conference on Learning Representations, pages 1–9, 2015.
  30. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems, pages 4077–4087, 2017.
  31. Yiming Tang and Yi Yu. Query-guided prototype learning with decoder alignment and dynamic fusion in few-fhot fegmentation. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(84):1–20, 2023.
  32. Differentiable meta-learning model for few-shot semantic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 12087–12094, 2020.
  33. Prior guided feature enrichment network for few-shot segmentation. volume 44, pages 1050–1065. IEEE, 2022.
  34. Panet: Few-shot image semantic segmentation with prototype alignment. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9197–9206, 2019.
  35. Tpsn: Transformer-based multi-prototype search network for few-shot semantic segmentation. Computers and Electrical Engineering, 103:108326, 2022.
  36. A novel surface defect inspection algorithm for magnetic tile. Applied Surface Science, 375:118–126, 2016.
  37. Mining latent classes for few-shot segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8721–8730, 2021.
  38. Mianet: Aggregating unbiased instance and general information for few-shot semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7131–7140, 2023.
  39. Brain-inspired gcn: modularity-based siamese simple graph convolutional networks. Information Sciences, 657:119971, 2024.
  40. Selective prototype network for few-shot metal surface defect segmentation. IEEE Transactions on Instrumentation and Measurement, 71:1–10, 2022.
  41. Convolutional neural networks rarely learn shape for semantic segmentation. Pattern Recognition, 146:110018, 2024.
  42. Canet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5217–5226, 2019.
  43. Sg-one: Similarity guidance network for one-shot semantic segmentation. IEEE Transactions on Cybernetics, 50(9):3855–3865, 2020.
  44. Generalizable model-agnostic semantic segmentation via target-specific normalization. Pattern Recognition, 122:108292, 2022.
  45. Prototype completion for few-shot learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10):12250–12268, 2023.
  46. Semantic segmentation of metal surface defects and corresponding strategies. IEEE Transactions on Instrumentation and Measurement, 72:1–13, 2023.
  47. Bmdenet: Bi-directional modality fifference elimination network for few-shot rgb-t semantic segmentation. IEEE Transactions on Circuits and Systems II: Express Briefs, 70(11):4266–4270, 2023.
  48. Dual graph reasoning network for oil leakage segmentation in substation equipment. IEEE Transactions on Instrumentation and Measurement, 73:1–15, 2023.
  49. Quaternion-valued correlation learning for few-shot semantic segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 33(5):2102–2115, 2023.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up