Student-Teacher Feature Pyramid Matching for Anomaly Detection
By Guodong Wang, Shumin Han, Errui Ding, Di Huang. British Machine Vision Conference, 2021
362 citations recorded by the source corpus.
Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies. This paper proposes a simple yet powerful approach to this issue, which is implemented in the student-teacher framework for its advantages but substantially extends it in terms of both accuracy and efficiency. Given a strong model pre-trained on image classification as the teacher, we distill the knowledge into a single student network with the identical architecture to learn the distribution of anomaly-free images and this one-step transfer preserves the crucial clues as much as possible. Moreover, we integrate the multi-scale feature matching strategy into the framework, and this hierarchical feature matching enables the student network to receive a mixture of multi-level knowledge from the feature pyramid under better supervision, thus allowing to detect anomalies of various sizes. The difference between feature pyramids generated by the two networks serves as a scoring function indicating the probability of anomaly occurring. Due to such operations, our approach achieves accurate and fast pixel-level anomaly detection. Very competitive results are delivered on the MVTec anomaly detection dataset, superior to the state of the art ones.
Subfields: General Health Professions, Philosophy
View Paper: https://www.semanticscholar.org/paper/02805f18989b7e77f30ee13defd6fecfcd0f499f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In General Health Professions
In Philosophy
Citations in the corpus
- Anomaly Detection via Reverse Distillation from One-Class Embedding (2022, methodology): “tation [23, 42, 46], knowledge distillation [4, 33, 39], etc.”
- EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies (2023, methodology): “To detect anomalous features, we use a student– teacher approach [10,53,65].”
- Revisiting Reverse Distillation for Anomaly Detection (2023, background): “STFPM [36] adapts a feature pyramid matching mechanism between the teacher network and the student counterpart.”
- A Unified Model for Multi-class Anomaly Detection (2022, methodology): “The outputs of the self-attention layer serve as the query of the cross-attention layer, and the encoder embeddings are used as the key and value of the cross-attention layer.”
- Deep Industrial Image Anomaly Detection: A Survey (2023, neutral): “While STPM [11] and MKD [10] both use multi-scale features under different network layers for distillation, they do so in different ways.”