Prototypical parts-based networks are becoming increasingly popular due ...
Multiple Instance Learning (MIL) is a weakly-supervised problem in which...
Nowadays artificial neural network models achieve remarkable results in ...
We introduce ProtoSeg, a novel model for interpretable semantic image
se...
Partial label learning is a type of weakly supervised learning, where ea...
Many crucial problems in deep learning and statistics are caused by a
va...
We introduce ProtoPool, an interpretable image classification model with...
Processing of missing data by modern neural networks, such as CNNs, rema...
Matrix decompositions are ubiquitous in machine learning, including
appl...
Structural fingerprints and pharmacophore modeling are methodologies tha...
We propose FlowSVDD – a flow-based one-class classifier for anomaly/outl...
Recent years have seen a surge in research on deep interpretable neural
...
Scanning real-life scenes with modern registration devices typically giv...
In this paper, we introduce ProtoPShare, a self-explained method that
in...
We investigate the problem of training neural networks from incomplete i...
We propose OneFlow - a flow-based one-class classifier for anomaly (outl...
We consider the problem of estimating the conditional probability
distri...
In the paper we construct a fully convolutional GAN model: LocoGAN, whic...
In this paper, we introduce a neural network framework for semi-supervis...
Graph Convolutional Networks (GCNs) have recently become the primary cho...
We show how to construct smooth and realistic interpolations for generat...
We construct a general unified framework for learning representation of
...
We propose a general, theoretically justified mechanism for processing
m...
In this paper, we analyze if cascade usage of the context encoder with
i...
In this paper, we focus on finding clusters in partially categorized dat...