Two data selection techniques (GMM visual similarity and bounding-box diversity) reduce required weakly labeled images by up to 100x on Open Images and 20x on Cityscapes while maintaining semantic segmentation performance.
Generative adversarial nets,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2019 4verdicts
UNVERDICTED 4roles
background 1polarities
unclear 1representative citing papers
Pseudo-rehearsal method with cGAN-generated old-concept samples, balanced online recall, and concept contrastive loss for class-incremental learning on MNIST, Fashion-MNIST and SVHN.
A route-specific deep generative model learns the probability distribution of bus trip ETAs from historical data alone and conditions updates on real-time trip progress.
A survey of 5G requirements, technologies and research for vertical automation domains with a short 6G outlook.
citing papers explorer
-
Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision
Two data selection techniques (GMM visual similarity and bounding-box diversity) reduce required weakly labeled images by up to 100x on Open Images and 20x on Cityscapes while maintaining semantic segmentation performance.
-
Incremental Concept Learning via Online Generative Memory Recall
Pseudo-rehearsal method with cGAN-generated old-concept samples, balanced online recall, and concept contrastive loss for class-incremental learning on MNIST, Fashion-MNIST and SVHN.
-
To each route its own ETA: A generative modeling framework for ETA prediction
A route-specific deep generative model learns the probability distribution of bus trip ETAs from historical data alone and conditions updates on real-time trip progress.
-
Next-generation Wireless Solutions for the Smart Factory, Smart Vehicles, the Smart Grid and Smart Cities
A survey of 5G requirements, technologies and research for vertical automation domains with a short 6G outlook.