Active learning aims to reduce labeling costs by selecting only the most...
Deep Neural Networks trained in a fully supervised fashion are the domin...
Deep Neural Networks (DNNs) often rely on very large datasets for traini...
This work addresses multi-class segmentation of indoor scenes with RGB-D...
We present the clustering learning technique applied to multi-layer
feed...
Numerous approaches in image processing and computer vision are making u...
Scene parsing, or semantic segmentation, consists in labeling each pixel...