Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Fei Ye et al.
Summary: With recent advances in deep neural networks, anomaly detection in multimedia has gained attention. This study proposes a new method that breaks the information equivalence between input and supervision by erasing selected attributes, allowing the network to learn semantic feature embeddings related to the erased attributes.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Liyang Chen et al.
Summary: This paper introduces UTRAD, a U-Transformer based Anomaly Detection framework that achieves a more stable training process and precise anomaly detection and localization results by reconstructing more informative feature distribution instead of raw images. UTRAD also reduces computational cost and memory usage with a multi-scale pyramidal hierarchy and skip connections.
Proceedings Paper
Computer Science, Artificial Intelligence
Zhuang Liu et al.
Summary: The development of visual recognition has gone through stages from ConvNets to ViTs and then to hybrid approaches. In this work, the design of a pure ConvNet is reexamined and several key components are discovered, resulting in the construction of the ConvNeXt model series. These models compete with Transformers in terms of accuracy and performance while maintaining the simplicity and efficiency of ConvNets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Nicolae-Catalin Ristea et al.
Summary: This paper proposes a novel self-supervised predictive architectural building block that can be integrated into various state-of-the-art anomaly detection methods. By predicting masked information and leveraging the reconstruction error as an abnormality score, the block achieves considerable performance improvements in image and video anomaly detection.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jonathan Pirnay et al.
Summary: Anomaly detection in computer vision aims to identify images that deviate from normal images. This paper proposes a patch-inpainting approach based on self-attention for anomaly detection. By inpainting covered patches in a sequence of image patches, the proposed method integrates information across large regions of the image.
IMAGE ANALYSIS AND PROCESSING, ICIAP 2022, PT II
(2022)
Article
Computer Science, Artificial Intelligence
Vitjan Zavrtanik et al.
Summary: The article discusses the issue of visual anomaly detection and the shortcomings of the auto-encoder method in reconstructing anomalous regions. A new approach (RIAD) is proposed to address this problem by reconstructing images through inpainting, setting a new state-of-the-art in anomaly detection benchmarks.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Yong Shi et al.
Summary: This paper proposes an effective unsupervised anomaly segmentation approach for detecting anomalies in small and confined regions of images. By leveraging regional feature generator and deep convolutional networks, the method achieves state-of-the-art performances on benchmark datasets and shows great potential for real applications.
Article
Computer Science, Theory & Methods
Tharindu Fernando et al.
Summary: This paper provides a thorough theoretical analysis of popular deep learning techniques in medical anomaly detection, comparing and contrasting their architectural differences as well as training algorithms. Additionally, it outlines the key limitations of existing deep medical anomaly detection techniques and proposes key research directions for further investigation.
ACM COMPUTING SURVEYS
(2021)
Proceedings Paper
Engineering, Industrial
Pankaj Mishra et al.
Summary: The study introduces a transformer-based image anomaly detection and localization network, along with a real-world industrial anomaly dataset BTAD. By preserving spatial information of embedded patches and utilizing a Gaussian mixture density network, the model is able to localize anomalous areas effectively.
PROCEEDINGS OF 2021 IEEE 30TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Marco Rudolph et al.
Summary: This study introduces a method called DifferNet that detects manufacturing errors by leveraging the descriptiveness of features extracted by convolutional neural networks. The method estimates density using normalizing flows and employs a multi-scale feature extractor to handle the high dimensionality of images, enabling pixel-wise localization.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Thomas Schlegl et al.
MEDICAL IMAGE ANALYSIS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Samet Akcay et al.
COMPUTER VISION - ACCV 2018, PT III
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Davide Abati et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
M. Haselmann et al.
2018 17TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA)
(2018)
Proceedings Paper
Computer Science, Information Systems
Thomas Schlegl et al.
INFORMATION PROCESSING IN MEDICAL IMAGING (IPMI 2017)
(2017)
Article
Computer Science, Artificial Intelligence
Wufeng Xue et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2014)
Article
Computer Science, Artificial Intelligence
Z Wang et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2004)