Home /
Research
Showing 535 - 540 / 897
Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
XuehuiWang, QingWang, YuzhiZhao....
Published date-11/13/2020
ImageSuper-Resolution, SuperResolution, Super-Resolution
Despite convolutional network-based methods have boosted the performance of single image super-resolution (SISR), the huge computation costs restrict their practical applicability. In this paper, we develop a computation efficient yet …
DeepMind Lab2D
CharlesBeattie, ThomasKöppe, EdgarA.Duéñez-Guzmán....
Published date-11/13/2020
We present DeepMind Lab2D, a scalable environment simulator for artificial intelligence research that facilitates researcher-led experimentation with environment design. DeepMind Lab2D was built with the specific needs of multi-agent deep …
A grammar compressor for collections of reads with applications to the construction of the BWT
DiegoDíaz-Domínguez, GonzaloNavarro....
Published date-11/13/2020
We describe a grammar for DNA sequencing reads from which we can compute the BWT directly. Our motivation is to perform in succinct space genomic analyses that require complex string …
Automatic segmentation with detection of local segmentation failures in cardiac MRI
JörgSander, BobD.deVos, IvanaIšgum....
Published date-11/13/2020
Segmentation of cardiac anatomical structures in cardiac magnetic resonance images (CMRI) is a prerequisite for automatic diagnosis and prognosis of cardiovascular diseases. To increase robustness and performance of segmentation methods …
Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis
DanielSeichter, MonaKöhler, BenjaminLewandowski....
Published date-11/13/2020
SemanticSegmentation
Analyzing scenes thoroughly is crucial for mobile robots acting in different environments. Semantic segmentation can enhance various subsequent tasks, such as (semantically assisted) person perception, (semantic) free space detection, (semantic) …
diagNNose: A Library for Neural Activation Analysis
JaapJumelet....
Published date-11/13/2020
In this paper we introduce diagNNose, an open source library for analysing the activations of deep neural networks. diagNNose contains a wide array of interpretability techniques that provide fundamental insights …