mlsanityData to 7 Oct 2026

Reconstruction Student with Attention for Student-Teacher Pyramid Matching

arXiv 2111.15376 ↗First posted 30 Nov 2021cs.CV eess.IVcited by 20

Not on the map. Why?

Abstract (arXiv)

Anomaly detection and localization are important problems in computer vision. Recently, Convolutional Neural Network (CNN) has been used for visual inspection. In particular, the scarcity of anomalous samples increases the difficulty of this task, and unsupervised leaning based methods are attracting attention. We focus on Student-Teacher Feature Pyramid Matching (STPM) which can be trained from only normal images with small number of epochs. Here we proposed a powerful method which compensates for the shortcomings of STPM. Proposed method consists of two students and two teachers that a pair of student-teacher network is the same as STPM. The other student-teacher network has a role to reconstruct the features of normal products. By reconstructing the features of normal products from an abnormal image, it is possible to detect abnormalities with higher accuracy by taking the difference between them. The new student-teacher network uses attention modules and different teacher network from the original STPM. Attention mechanism acts to successfully reconstruct the normal regions in an input image. Different teacher network prevents looking at the same regions as the original STPM. Six anomaly maps obtained from the two student-teacher networks are used to calculate the final anomaly map. Student-teacher network for reconstructing features improved AUC scores for pixel level and image level in comparison with the original STPM.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

21 of 33 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  6. 2014Conditional Generative Adversarial Netscited by 2,152
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  8. 2018Self-Attention Generative Adversarial Networkscited by 809
  9. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 572
  10. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  11. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  12. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
9 more
  1. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  2. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  3. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  4. 2018Attention Branch Network: Learning of Attention Mechanism for Visual Explanationcited by 108
  5. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  6. 2018An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videoscited by 45
  7. 2017Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowdscited by 28
  8. 2018Metric Learning for Novelty and Anomaly Detectioncited by 21
  9. 2019Accuracy Booster: Performance Boosting using Feature Map Re-calibrationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 3; 2025: 5; 2026: 2.

20 papers.

Sort:

By area:

  1. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  2. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  3. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 81
  4. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  5. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  6. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detectioncited by 33
  7. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  8. 2022MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detectioncited by 19
  9. 2023What makes a good data augmentation for few-shot unsupervised image anomaly detection?cited by 8
  10. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  11. 2022Unsupervised Visual Defect Detection with Score-Based Generative Modelcited by 7
  12. 2024MedDiff-FM: A Diffusion-based Foundation Model for Versatile Medical Image Applicationscited by 7
8 more
  1. 2025Is Hyperbolic Space All You Need for Medical Anomaly Detection?cited by 5
  2. 2023MixedTeacher : Knowledge Distillation for fast inference textural anomaly detectioncited by 2
  3. 2024A Recover-then-Discriminate Framework for Robust Anomaly Detectioncited by 2
  4. 2025Q-Former Autoencoder: A Modern Framework for Medical Anomaly Detectioncited by 2
  5. 2025Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Datacited by 1
  6. 2025Teacher Encoder-Student Decoder Denoising Guided Segmentation Network for Anomaly Detectioncited by 0
  7. 2026Novel Anomaly Detection Scenarios and Evaluation Metrics to Address the Ambiguity in the Definition of Normal Samplescited by 0
  8. 2026MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectorscited by 0