Homography estimation is a basic image-alignment method in many applicat...
Convolutional neural networks (CNNs) have been successfully applied to c...
We propose a novel semi-supervised learning approach for classification ...
Most adversarial attack defense methods rely on obfuscating gradients. T...
The interpretability of medical image analysis models is considered a ke...
Adversarial training, especially projected gradient descent (PGD), has b...
The high complexity of deep learning models is associated with the diffi...
We introduce the idea of inter-slice image augmentation whereby the numb...
Knowledge of what spatial elements of medical images deep learning metho...
In medical applications, the same anatomical structures may be observed ...
Data driven segmentation is an important initial step of shape prior-bas...
In this paper, we propose an efficient pseudo-marginal Markov chain Mont...
We present a neighborhood similarity layer (NSL) which induces appearanc...
Segmenting images of low quality or with missing data is a challenging
p...
Region-based methods have proven necessary for improving segmentation
ac...
Level set methods are widely used for image segmentation because of thei...
Decomposition of shapes into (approximate) convex parts is essential for...
Effective convolutional neural networks are trained on large sets of lab...
In this paper we consider the problem of semi-supervised learning with d...
Artificial neural networks are powerful pattern classifiers; however, th...
Scene labeling is the problem of assigning an object label to each pixel...