• Corpus ID: 233423406

Inpainting Transformer for Anomaly Detection

@article{Pirnay2021InpaintingTF,
  title={Inpainting Transformer for Anomaly Detection},
  author={Jonathan Pirnay and Keng Yip Chai},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.13897}
}
Anomaly detection in computer vision is the task of identifying images which deviate from a set of normal images. A common approach is to train deep convolutional autoencoders to inpaint covered parts of an image and compare the output with the original image. By training on anomaly-free samples only, the model is assumed to not being able to reconstruct anomalous regions properly. For anomaly detection by inpainting we suggest it to be beneficial to incorporate information from potentially… 

Figures and Tables from this paper

Multi-Scale Patch-Based Representation Learning for Image Anomaly Detection and Segmentation
TLDR
A multi-scale patch-based representation learning method to extract critical and representative information from normal images by taking the relative feature similarity between patches of different local distances into account, thus allowing the model to learn better geometric relationship between neighboring patches.
A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection
TLDR
The end goal of this work is the detection of subtle defects in leather samples for the automotive industry, and it is shown that the same algorithm achieves state-of-the-art results in public anomalies datasets.
Unsupervised Anomaly Detection and Segmentation on Dirty Datasets
TLDR
This paper proposes an unsupervised framework to solve the industrial anomaly detection and segmentation problem when the training set contains anomaly samples, and uses a model pretrained on ImageNet as a feature extractor to extract patch-level features.
Transformaly - Two (Feature Spaces) Are Better Than One
TLDR
Transformationaly exploits a pre-trained Vision Transformer to extract both feature vectors: the pre- trained (agnostic) features and the teacher-student (fine-tuned) features, and reports state-of-the-art AUROC results.
Diffusion Models for Medical Anomaly Detection
TLDR
This work combines the deterministic iterative noising and denoising scheme with classifier guidance for image-to-image translation between diseased and healthy subjects and generates very detailed anomaly maps without the need for a complex training procedure.
MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities
TLDR
In order to fully fuse the memory information with the high-level features of the input image, MemSeg introduces a multi-scale feature fusion module (MSFF Module) and a novel spatial attention module, which greatly improves the model precision of anomaly localization.
Surface Defect Detection Methods for Industrial Products: A Review
TLDR
The commonly used datasets of industrial surface defects in recent years are more comprehensively summarized, and the latest research methods on the MVTec AD dataset are compared, so as to provide some reference for the further research and development ofindustrial surface defect detection technology.
A Survey on Unsupervised Industrial Anomaly Detection Algorithms
TLDR
A thorough overview of recently proposed unsupervised algorithms for visual anomaly detection covering categories, whose innovation points and frameworks are described in detail are provided and expected to assist both the research community and industry in developing a broader and cross-domain perspective.
Data refinement for fully unsupervised visual inspection using pre-trained networks
TLDR
This work first assesses the robustness of these pre-trained methods to fully unsupervised context, using polluted training sets, and shows that these methods are more robust to pollution compared to methods such as CutPaste, and proposes SROC, a Simple Refinement strategy for One Class classification.
Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
TLDR
A novel Omni-frequency Channel-selection Reconstruction (OCR-GAN) network to handle anomaly detection task in a perspective of frequency and model the reconstruction process as a combination of parallel omnifrequency image restorations as the authors observe a significant difference in the frequency distribution of normal and abnormal images.
...
1
2
...

References

SHOWING 1-10 OF 57 REFERENCES
Reconstruction by inpainting for visual anomaly detection
MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
TLDR
This work introduces the MVTec Anomaly Detection (MVTec AD) dataset containing 5354 high-resolution color images of different object and texture categories, and conducts a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods based on deep architectures such as convolutional autoencoders, generative adversarial networks, and feature descriptors using pre-trained convolved neural networks.
Anomaly detection of defects on concrete structures with the convolutional autoencoder
Anomaly Detection Using Deep Learning Based Image Completion
TLDR
Results on surface images of decorated plastic parts demonstrate that this one-class unsupervised learning on fault-free samples is suitable for detection of visible anomalies and moreover surpasses all other tested methods.
Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection
TLDR
This work introduces an unsupervised anomaly detection model, trained only on the normal (non-anomalous, plentiful) samples in order to learn the normality distribution of the domain, and hence detect abnormality based on deviation from this model.
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
TLDR
This work proposes a two-stage framework for building anomaly detectors using normal training data only, which first learns self-supervised deep representations and then builds a generative one-class classifier on learned representations.
GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
TLDR
This work introduces a novel anomaly detection model, by using a conditional generative adversarial network that jointly learns the generation of high-dimensional image space and the inference of latent space and shows the model efficacy and superiority over previous state-of-the-art approaches.
Unsupervised Region-Based Anomaly Detection In Brain MRI With Adversarial Image Inpainting
TLDR
A fully automatic, unsupervised inpainting-based brain tumour segmentation system for T1-weighted MRI that is able to segment various sized and abstract tumours and achieves a mean and standard deviation Dice score of 0.771 and 0.176, respectively.
Generative Image Inpainting with Contextual Attention
TLDR
This work proposes a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.
PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization
TLDR
PaDiM outperforms current state-of-the-art approaches for both anomaly detection and localization on the MVTec AD and STC datasets and is a good candidate for many industrial applications.
...
1
2
3
4
5
...