• Corpus ID: 237371526

Looking at the whole picture: constrained unsupervised anomaly segmentation

@article{SilvaRodriguez2021LookingAT,
  title={Looking at the whole picture: constrained unsupervised anomaly segmentation},
  author={Julio Silva-Rodr'iguez and Valery Naranjo and Jos{\'e} Dolz},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.00482}
}
Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. However, a main limitation of nearly all prior literature is the need of employing anomalous images to set a class-specific threshold to locate the anomalies. This limits their usability in realistic scenarios, where only normal data is typically accessible. Despite… 

References

SHOWING 1-10 OF 40 REFERENCES
Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study
TLDR
A ranking of the methods in the field of Unsupervised Anomaly Detection in brain MRI by utilizing a single architecture, a single resolution and the same dataset(s) is provided, to establish comparability among recent methods.
Attention Guided Anomaly Localization in Images
TLDR
This work proposes Convolutional Adversarial Variational autoencoder with Guided Attention (CAVGA), which localizes the anomaly with a convolutional latent variable to preserve the spatial information and outperforms state-of-the-art anomaly localization methods on several datasets.
Towards Visually Explaining Variational Autoencoders
  • WenQian Liu, Runze Li, +5 authors O. Camps
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
TLDR
This work proposes the first technique to visually explain VAEs by means of gradient-based attention, and presents methods to generate visual attention from the learned latent space, and shows how such attention explanations serve more than just explaining VAE predictions.
f‐AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks
TLDR
Fast AnoGAN (f‐AnoGAN), a generative adversarial network (GAN) based unsupervised learning approach capable of identifying anomalous images and image segments, that can serve as imaging biomarker candidates is presented.
Unsupervised Lesion Detection via Image Restoration with a Normative Prior
TLDR
A probabilistic model that uses a network-based prior as the normative distribution and detect lesions pixel-wise using MAP estimation is proposed and outperforms the state-of-the-art unsupervised methods by a substantial margin.
Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders
TLDR
This work uses the Human Connectome Project dataset to learn distribution of healthy-appearing brain MRI and proposes a simple yet effective constraint that helps mapping of an image bearing lesion close to its corresponding healthy image in the latent space.
Unsupervised Lesion Detection in Brain CT using Bayesian Convolutional Autoencoders
TLDR
This work explores the use of Bayesian autoencoders to learn the variability of healthy tissue and detect lesions as unlikely events under the normative model and results indicate that the method achieves best performance in detecting lesions caused by bleeding compared to baselines.
Constrained‐CNN losses for weakly supervised segmentation☆
TLDR
A differentiable penalty is proposed, which enforces inequality constraints directly in the loss function, avoiding expensive Lagrangian dual iterates and proposal generation and has the potential to close the gap between weakly and fully supervised learning in semantic medical image segmentation.
Abstract: Unsupervised Anomaly Localization Using Variational Auto-Encoders
TLDR
Deep learning and especially Variational Auto-Encoders have shown great potential in the unsupervised learning of data distributions and in principle this allows for an assumption-free automatic check of medical images for potentially overseen anomalies.
An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection
TLDR
This work proposes a medical image synthesis model named abnormal-to-normal translation generative adversarial network (ANT-GAN) to generate a normal-looking medical image based on its abnormal-looking counterpart without the need for paired training data.
...
1
2
3
4
...