ViewPCL uses Wasserstein distance between cross-view point cloud distributions as an uncertainty score, and it reports higher mIoU than ViewAL on SceneNet-RGBD.
Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically principled, BNNs require approximations to be applied to large-scale problems, where both performance and uncertainty estimation are crucial. In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep BNN. We conduct a series of large-scale visual active learning experiments to evaluate DPEs on classification with the CIFAR-10, CIFAR-100 and ImageNet datasets, and semantic segmentation with the BDD100k dataset. Our models require significantly less training data to achieve competitive performances, and steadily improve upon strong active learning baselines as the annotation budget is increased.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ViewPCL: a point cloud based active learning method for multi-view segmentation
ViewPCL uses Wasserstein distance between cross-view point cloud distributions as an uncertainty score, and it reports higher mIoU than ViewAL on SceneNet-RGBD.