Metro Anomaly Detection Based on Light Strip Inductive Key Frame Extraction and MAGAN Network

Liu, Ruikang; Liu, Weiming; Li, Haiyu; Wang, Heng; Geng, Qinghua; Dai, Yuan

doi:10.1109/tim.2021.3128961

Cited by 12 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By designing a S-Net to transfer the feature extraction capability of the pre-trained model, and the exclusive use of normal samples for training, the T-Net and S-Net in the T-S model are capable of producing distinct features for abnormal images. In order to obtain multi-scale abnormal features, US [18] uses an ensemble learning method, while STPM [29] and MKD [30] choose to calculate multi-scale feature differences. Kohei et al [62] further improve the model in [29] using consistency between layer groups.…”

Section: Knowledge Distillation-based Methodsmentioning

confidence: 99%

Anomaly Detection for Medical Images Using Teacher–Student Model With Skip Connections and Multiscale Anomaly Consistency

Liu,

Jiao,

et al. 2024

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Anomaly detection (AD) in medical images aims to recognize test-time abnormal inputs according to normal samples in the training set. Knowledge distillation based on the teacher-student (T-S) model is a simple and effective method to identify anomalies, yet its efficacy is constrained by the similarity between teacher and student network architectures. To address this problem, in this paper, we propose a T-S model with skip connections (Skip-TS) which is trained by direct reverse knowledge distillation (DRKD) for AD in medical images. First, to overcome the low sensitivity to anomalies caused by structural similarity, we design an encoder-decoder architecture where the teacher network (T-Net) is a pre-trained encoder and the student network (S-Net) is a randomly initialized decoder. During training, the S-Net learns to reconstruct the shallow representations of images from the output of the T-Net, which is called DRKD. Secondly, we introduce skip connections to the T-S model to prevent the S-Net from missing normal information of images at multiscale. In addition, we design a multi-scale anomaly consistency (MAC) loss to improve the anomaly detection and localization performance. Thorough experiments conducted on twelve public medical datasets and two private medical datasets demonstrate that our approach surpasses the current state-of-the-art by 6.4% and 8.2% in terms of AUROC on public and private datasets, respectively. Code and organized benchmark datasets will be available at https://github.com/Arktis2022/Skip-TS.

show abstract

Section: Knowledge Distillation-based Methodsmentioning

confidence: 99%

Anomaly Detection for Medical Images Using Teacher–Student Model With Skip Connections and Multiscale Anomaly Consistency

Liu,

Jiao,

et al. 2024

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…By designing a S-Net to transfer the feature extraction capability of the pre-trained model, and the exclusive use of normal samples for training, the T-Net and S-Net in the T-S model are capable of producing distinct features for abnormal images. In order to obtain multi-scale abnormal features, US [18] uses an ensemble learning method, while STPM [28] and MKD [29] choose to calculate multi-scale feature differences. Kohei et al [56] further improve the model in [28] using consistency between layer groups.…”

Section: Knowledge Distillation-based Methodsmentioning

confidence: 99%

Anomaly Detection for Medical Images Using Teacher-Student Model with Skip Connections and Multi-scale Anomaly Consistency

Liu,

Jiao,

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Anomaly detection (AD) in medical images aims to recognize test-time abnormal inputs according to normal samples in the training set. Knowledge distillation based on the teacher-student (T-S) model is a simple and effective method to identify anomalies, yet its efficacy is constrained by the similarity between teacher and student network architectures. To address this problem, in this paper, we propose a T-S model with skip connections (Skip-TS) which is trained by direct reverse knowledge distillation (DRKD) for AD in medical images. First, to overcome the low sensitivity to anomalies caused by structural similarity, we design an encoder-decoder architecture where the teacher network (T-Net) is a pre-trained encoder and the student network (S-Net) is a randomly initialized decoder. During training, the S-Net learns to reconstruct the shallow representations of images from the output of the T-Net, which is called DRKD. Secondly, we introduce skip connections to the T-S model to prevent the S-Net from missing normal information of images at multi-scale. In addition, we design a multi-scale anomaly consistency (MAC) loss to improve the anomaly detection and localization performance. Thorough experiments conducted on twelve public medical datasets and two private medical datasets demonstrate that our approach surpasses the current state-of-the-art by 6.4% and 8.2% in terms of AUROC on public and private datasets, respectively. Code and organized benchmark datasets will be available at https://github.com/Arktis2022/Skip-TS.</p>

show abstract

“…The image space-based methods compare the difference between the input and reconstructed images in a pixel-bypixel or patch-by-patch manner to highlight potential abnormal areas. Liu et al [33] designed an unsupervised network based on a dilating fine-grained generator (a nested U-Net [34] structure), a multipatch discriminator, and a local-attentive reconstruction loss. The proposed generator largely suppresses the reconstruction of anomalies.…”

Section: Related Workmentioning

confidence: 99%

Intercity Railway Risk Space Anomaly Detection Based on Train Predeparture Key Frame Extraction and IADN Network

Duan

Liu

et al. 2023

IEEE Sensors J.

View full text Add to dashboard Cite

Anomalies between the platform doors and train seriously threaten the safe operation of intercity railway train, and therefore, accurately selecting the appropriate time for anomaly detection in elaborate process of train access is vital. However, the scarcity of data samples, disadvantage of anomaly reconstruction, and unreliable reconstruction errors pose challenges to image reconstruction-based anomaly detection methods. To address these issues, this study proposes a method based on train predeparture key frame extraction and patch-level unsupervised network using image inpainting. The key frame extraction is designed to extract the key frame to assist subsequent detection by tracking the motion state of train door and converting states into the switching door signals. An unsupervised network, which named image-inpainting anomaly detection network (IADN), based on image-inpainting autoencoder (AE), local abnormal information enhancement, and global-attentive reconstruction error (GARE), is proposed for anomaly classification and localization. The network utilizes an image-inpainting AE based on masking strategy and dual-channel structure to reconstruct normal images and solve the anomaly reconstruction problem. Afterward, it proposes local abnormal information enhancement and GARE to enhance the difference between inputs and reconstructions to improve the accuracy. The proposed method is tested on the intercity railway risk space anomaly dataset, and the anomaly classification AUC, localization precision, and recall achieve 99.32%, 97.45%, and 96.29%, respectively, which outperforms state-of-the-art methods.

show abstract

Metro Anomaly Detection Based on Light Strip Inductive Key Frame Extraction and MAGAN Network

Cited by 12 publications

References 47 publications

Anomaly Detection for Medical Images Using Teacher–Student Model With Skip Connections and Multiscale Anomaly Consistency

Anomaly Detection for Medical Images Using Teacher–Student Model With Skip Connections and Multiscale Anomaly Consistency

Anomaly Detection for Medical Images Using Teacher-Student Model with Skip Connections and Multi-scale Anomaly Consistency

Intercity Railway Risk Space Anomaly Detection Based on Train Predeparture Key Frame Extraction and IADN Network

Contact Info

Product

Resources

About