
-
FroDO: From Detections to 3D Objects
Object-oriented maps are important for scene understanding since they jo...
read it
-
Multiphase flow prediction with deep neural networks
This paper proposes a deep neural network approach for predicting multip...
read it
-
A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems
A deep-learning-based surrogate model is developed and applied for predi...
read it
-
Learning Compressed Sentence Representations for On-Device Text Processing
Vector representations of sentences, trained on massive text corpora, ar...
read it
-
ADM for grid CRF loss in CNN segmentation
Variants of gradient descent (GD) dominate CNN loss minimization in comp...
read it
-
Constrained-CNN losses forweakly supervised segmentation
Weak supervision, e.g., in the form of partial labels or image tags, is ...
read it
-
Normalized Cut Loss for Weakly-supervised CNN Segmentation
Most recent semantic segmentation methods train deep convolutional neura...
read it
-
On Regularized Losses for Weakly-supervised CNN Segmentation
Minimization of regularized losses is a principled approach to weak supe...
read it
-
Kernel clustering: density biases and solutions
Kernel methods are popular in clustering due to their generality and dis...
read it
-
Kernel Cuts: MRF meets Kernel & Spectral Clustering
We propose a new segmentation model combining common regularization ener...
read it