
AOWS: Adaptive and optimal network width search with latency constraints
Neural architecture search (NAS) approaches aim at automatically finding...
read it

Discriminative training of conditional random fields with probably submodular constraints
Problems of segmentation, denoising, registration and 3D reconstruction ...
read it

Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory Practice
The Dice score and Jaccard index are commonly used metrics for the evalu...
read it

Adaptive Compressionbased Lifelong Learning
The problem of a deep learning model losing performance on a previously ...
read it

Generating superpixels using deep image representations
Superpixel algorithms are a common preprocessing step for computer visi...
read it

MultiGrain: a unified image embedding for classes and instances
MultiGrain is a network architecture producing compact vector representa...
read it

Yes, IoU loss is submodular  as a function of the mispredictions
This note is a response to [7] in which it is claimed that [13, Proposit...
read it

Supermodular Locality Sensitive Hashes
In this work, we show deep connections between Locality Sensitive Hashab...
read it

Efficient semantic image segmentation with superpixel pooling
In this work, we evaluate the use of superpixel pooling layers in deep n...
read it

Stochastic Weighted Function Norm Regularization
Deep neural networks (DNNs) have become increasingly important due to th...
read it

Optimization of the Jaccard index for image segmentation with the Lovász hinge
The Jaccard loss, commonly referred to as the intersectionoverunion lo...
read it
Maxim Berman
is this you? claim profile