scholarly journals Explaining the Black-box Smoothly- A Counterfactual Approach

2021 ◽  
Author(s):  
Sumedha Singla ◽  
Brian Pollack ◽  
Stephen Wallace ◽  
Kayhan Batmanghelich
Keyword(s):  
Generative Adversarial Networks ◽  
Query Image ◽  
Adversarial Networks ◽  
Saliency Maps ◽  
Extensive Evaluation ◽  
Chest X Ray ◽  
Healthcare Application ◽  
Original Class ◽  
The Given ◽  
Counterfactual Approach

<p>We propose a BlackBox <i>Counterfactual Explainer</i> that is explicitly developed for medical imaging applications. Classical approaches (<i>e.g.,</i> saliency maps) assessing feature importance do not explain <i>how</i> and <i>why</i> variations in a particular anatomical region are relevant to the outcome, which is crucial for transparent decision making in healthcare application. Our framework explains the outcome by gradually <i>exaggerating</i> the semantic effect of the given outcome label. Given a query input to a classifier, Generative Adversarial Networks produce a progressive set of perturbations to the query image that gradually changes the posterior probability from its original class to its negation. We design the loss function to ensure that essential and potentially relevant details, such as support devices, are preserved in the counterfactually generated images. We provide an extensive evaluation of different classification tasks on the chest X-Ray images. Our experiments show that a counterfactually generated visual explanation is consistent with the disease's clinical relevant measurements, both quantitatively and qualitatively.</p>

scholarly journals Explaining the Black-box Smoothly- A Counterfactual Approach

2021 ◽  
Author(s):  
Sumedha Singla ◽  
Brian Pollack ◽  
Stephen Wallace ◽  
Kayhan Batmanghelich
Keyword(s):  
Generative Adversarial Networks ◽  
Query Image ◽  
Adversarial Networks ◽  
Saliency Maps ◽  
Extensive Evaluation ◽  
Chest X Ray ◽  
Healthcare Application ◽  
Original Class ◽  
The Given ◽  
Counterfactual Approach

<p>We propose a BlackBox <i>Counterfactual Explainer</i> that is explicitly developed for medical imaging applications. Classical approaches (<i>e.g.,</i> saliency maps) assessing feature importance do not explain <i>how</i> and <i>why</i> variations in a particular anatomical region are relevant to the outcome, which is crucial for transparent decision making in healthcare application. Our framework explains the outcome by gradually <i>exaggerating</i> the semantic effect of the given outcome label. Given a query input to a classifier, Generative Adversarial Networks produce a progressive set of perturbations to the query image that gradually changes the posterior probability from its original class to its negation. We design the loss function to ensure that essential and potentially relevant details, such as support devices, are preserved in the counterfactually generated images. We provide an extensive evaluation of different classification tasks on the chest X-Ray images. Our experiments show that a counterfactually generated visual explanation is consistent with the disease's clinical relevant measurements, both quantitatively and qualitatively.</p>

scholarly journals Deep Convolutional Generative Modeling for Artificial Microstructure Development of Aluminum-Silicon Alloy

2021 ◽  
Vol 1 (1) ◽  
pp. 1-6
Author(s):  
Akshansh Mishra ◽  
Tarushi Pathak
Keyword(s):  
Machine Learning ◽  
Generative Adversarial Networks ◽  
Microstructure Development ◽  
Machine Learning Technique ◽  
Silicon Alloy ◽  
Aluminum Silicon Alloy ◽  
Adversarial Networks ◽  
Generative Modeling ◽  
Learning Technique ◽  
The Given

Machine learning which is a sub-domain of an Artificial Intelligence which is finding various applications in manufacturing and material science sectors. In the present study, Deep Generative Modeling which a type of unsupervised machine learning technique has been adapted for the constructing the artificial microstructure of Aluminium-Silicon alloy. Deep Generative Adversarial Networks has been used for developing the artificial microstructure of the given microstructure image dataset. The results obtained showed that the developed models had learnt to replicate the lining near the certain images of the microstructures.

scholarly journals Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 153535-153545
Author(s):  
Faizan Munawar ◽  
Shoaib Azmat ◽  
Talha Iqbal ◽  
Christer Gronlund ◽  
Hazrat Ali
Keyword(s):  
Generative Adversarial Networks ◽  
X Ray ◽  
Adversarial Networks ◽  
Chest X Ray

scholarly journals A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation

Mathematics ◽  
2021 ◽  
Vol 9 (22) ◽  
pp. 2896
Author(s):  
Giorgio Ciano ◽  
Paolo Andreini ◽  
Tommaso Mazzierli ◽  
Monica Bianchini ◽  
Franco Scarselli
Keyword(s):  
Data Augmentation ◽  
Semantic Segmentation ◽  
Generative Adversarial Networks ◽  
Radiographic Images ◽  
X Ray ◽  
Adversarial Networks ◽  
Multi Stage ◽  
Segmentation Methods ◽  
Chest X Ray ◽  
Time Required

Multi-organ segmentation of X-ray images is of fundamental importance for computer aided diagnosis systems. However, the most advanced semantic segmentation methods rely on deep learning and require a huge amount of labeled images, which are rarely available due to both the high cost of human resources and the time required for labeling. In this paper, we present a novel multi-stage generation algorithm based on Generative Adversarial Networks (GANs) that can produce synthetic images along with their semantic labels and can be used for data augmentation. The main feature of the method is that, unlike other approaches, generation occurs in several stages, which simplifies the procedure and allows it to be used on very small datasets. The method was evaluated on the segmentation of chest radiographic images, showing promising results. The multi-stage approach achieves state-of-the-art and, when very few images are used to train the GANs, outperforms the corresponding single-stage approach.

scholarly journals Deep Convolutional Generative Modeling for Artificial Microstructure Development of Aluminum-Silicon Alloy

2021 ◽  
pp. 1-6
Author(s):  
Akshansh Mishra ◽  
◽  
Tarushi Pathak ◽  
Keyword(s):  
Machine Learning ◽  
Generative Adversarial Networks ◽  
Microstructure Development ◽  
Machine Learning Technique ◽  
Silicon Alloy ◽  
Aluminum Silicon Alloy ◽  
Adversarial Networks ◽  
Generative Modeling ◽  
Learning Technique ◽  
The Given

Machine learning which is a sub-domain of an Artificial Intelligence which is finding various applications in manufacturing and material science sectors. In the present study, Deep Generative Modeling which a type of unsupervised machine learning technique has been adapted for the constructing the artificial microstructure of Aluminium-Silicon alloy. Deep Generative Adversarial Networks has been used for developing the artificial microstructure of the given microstructure image dataset. The results obtained showed that the developed models had learnt to replicate the lining near the certain images of the microstructures.

scholarly journals Weakly Supervised GAN for Image-to-Image Translation in the Wild

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Zhiyi Cao ◽  
Shaozhang Niu ◽  
Jiwei Zhang
Keyword(s):  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Image Translation ◽  
Latent Space ◽  
In The Wild ◽  
Adversarial Examples ◽  
Weakly Supervised ◽  
Public Datasets ◽  
Global And Local ◽  
The Given

Generative Adversarial Networks (GANs) have achieved significant success in unsupervised image-to-image translation between given categories (e.g., zebras to horses). Previous GANs models assume that the shared latent space between different categories will be captured from the given categories. Unfortunately, besides the well-designed datasets from given categories, many examples come from different wild categories (e.g., cats to dogs) holding special shapes and sizes (short for adversarial examples), so the shared latent space is troublesome to capture, and it will cause the collapse of these models. For this problem, we assume the shared latent space can be classified as global and local and design a weakly supervised Similar GANs (Sim-GAN) to capture the local shared latent space rather than the global shared latent space. For the well-designed datasets, the local shared latent space is close to the global shared latent space. For the wild datasets, we will get the local shared latent space to stop the model from collapse. Experiments on four public datasets show that our model significantly outperforms state-of-the-art baseline methods.

Sign in / Sign up

Export Citation Format

Share Document