Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection (2312.13783v2)

Published 21 Dec 2023 in cs.CV, cs.AI, and cs.LG

Abstract: Logical anomalies (LA) refer to data violating underlying logical constraints e.g., the quantity, arrangement, or composition of components within an image. Detecting accurately such anomalies requires models to reason about various component types through segmentation. However, curation of pixel-level annotations for semantic segmentation is both time-consuming and expensive. Although there are some prior few-shot or unsupervised co-part segmentation algorithms, they often fail on images with industrial object. These images have components with similar textures and shapes, and a precise differentiation proves challenging. In this study, we introduce a novel component segmentation model for LA detection that leverages a few labeled samples and unlabeled images sharing logical constraints. To ensure consistent segmentation across unlabeled images, we employ a histogram matching loss in conjunction with an entropy loss. As segmentation predictions play a crucial role, we propose to enhance both local and global sample validity detection by capturing key aspects from visual semantics via three memory banks: class histograms, component composition embeddings and patch-level representations. For effective LA detection, we propose an adaptive scaling strategy to standardize anomaly scores from different memory banks in inference. Extensive experiments on the public benchmark MVTec LOCO AD reveal our method achieves 98.1% AUROC in LA detection vs. 89.6% from competing methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126.
  2. Beyond dents and scratches: Logical constraints in unsupervised anomaly detection and localization. International Journal of Computer Vision, 130(4): 947–969.
  3. MVTec AD–A comprehensive real-world dataset for unsupervised anomaly detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 9592–9600.
  4. Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4183–4192.
  5. Few-shot segmentation without meta-learning: A good transductive inference is all you need? In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 13979–13988.
  6. Albumentations: fast and flexible image augmentations. Information, 11(2): 125.
  7. Detect what you can: Detecting and representing objects using holistic models and body parts. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1971–1978.
  8. Padim: a patch distribution modeling framework for anomaly detection and localization. In International Conference on Pattern Recognition, 475–489. Springer.
  9. Anomaly detection via reverse distillation from one-class embedding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9737–9746.
  10. Unsupervised co-part segmentation through assembly. In International Conference on Machine Learning, 3576–3586. PMLR.
  11. Leveraging GAN priors for few-shot part segmentation. In Proceedings of the 30th ACM International Conference on Multimedia, 1339–1347.
  12. Cost aggregation with 4d convolutional swin transformer for few-shot segmentation. In European Conference on Computer Vision, 108–126. Springer.
  13. Huang, Y.; et al. 2020. Surface defect saliency of magnetic tile. The Visual Computer, 36: 85–96.
  14. Scops: Self-supervised co-part segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 869–878.
  15. ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection. arXiv preprint arXiv:2305.16713.
  16. Softpatch: Unsupervised anomaly detection with noisy data. Advances in Neural Information Processing Systems, 35: 15433–15445.
  17. Uncertainty-aware semi-supervised few shot segmentation. Pattern Recognition, 137: 109292.
  18. Cfa: Coupled-hypersphere-based feature adaptation for target-oriented anomaly localization. IEEE Access, 10: 78446–78454.
  19. Cutpaste: Self-supervised learning for anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9664–9674.
  20. Component-aware anomaly detection framework for adjustable and logical industrial visual inspection. arXiv preprint arXiv:2305.08509.
  21. Diversity-measurable anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12147–12156.
  22. Few-shot 3d multi-modal medical image segmentation using generative adversarial learning. arXiv preprint arXiv:1810.12241.
  23. Towards total recall in industrial anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 14318–14328.
  24. Asymmetric student-teacher networks for industrial anomaly detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2592–2602.
  25. One-shot learning for semantic segmentation. arXiv preprint arXiv:1709.03410.
  26. Motion-supervised co-part segmentation. In 2020 25th International Conference on Pattern Recognition (ICPR), 9650–9657. IEEE.
  27. Generalized nonnegative matrix approximations with Bregman divergences. Advances in neural information processing systems, 18.
  28. Revisiting reverse distillation for anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 24511–24520.
  29. Tritrong, N.; et al. 2021. Repurposing gans for one-shot semantic part segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4475–4485.
  30. Tsai, C.-C.; et al. 2022. Multi-scale patch-based representation learning for image anomaly detection and segmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 3992–4000.
  31. Set features for fine-grained anomaly detection. arXiv preprint arXiv:2302.12245.
  32. Seggpt: Segmenting everything in context. arXiv preprint arXiv:2304.03284.
  33. Semi-supervised semantic segmentation using unreliable pseudo-labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4248–4257.
  34. SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification. arXiv preprint arXiv:2305.00398.
  35. Wide residual networks. arXiv preprint arXiv:1605.07146.
  36. Zavrtanik, V.; et al. 2021. Draem-a discriminatively trained reconstruction embedding for surface anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 8330–8339.
Citations (12)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now