As natural images usually contain multiple objects, multi-label image
cl...
In many medical imaging and classical computer vision tasks, the Dice sc...
Neural architecture search (NAS) approaches aim at automatically finding...
Problems of segmentation, denoising, registration and 3D reconstruction ...
The Dice score and Jaccard index are commonly used metrics for the evalu...
The problem of a deep learning model losing performance on a previously
...
Superpixel algorithms are a common pre-processing step for computer visi...
MultiGrain is a network architecture producing compact vector representa...
This note is a response to [7] in which it is claimed that [13, Proposit...
In this work, we show deep connections between Locality Sensitive Hashab...
In this work, we evaluate the use of superpixel pooling layers in deep
n...
Deep neural networks (DNNs) have become increasingly important due to th...
The Jaccard loss, commonly referred to as the intersection-over-union lo...