paper-with-me

홈 › Papers

Depth Uncertainty Networks for Active Learning

2021-12-13 · Chelsea Murray, James U. Allingham, Javier Antorán, José Miguel Hernández-Lobato

In active learning, the size and complexity of the training dataset changes over time. Simple models that are well specified by the amount of data available at the start of active learning might suffer from bias as more points are actively sampled. Flexible models that might be well suited to the full dataset can suffer from overfitting towards the start of active learning. We tackle this problem using Depth Uncertainty Networks (DUNs), a BNN variant in which the depth of the network, and thus its complexity, is inferred. We find that DUNs outperform other BNN variants on several active learning tasks. Importantly, we show that on the tasks in which DUNs perform best they present notably less overfitting than baselines.

📄 PDF Abstract BibTeX arXiv:2112.06796

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

DEUX: Active Exploration for Learning Unsupervised Depth Perception

2023-09-16 · Marvin Chancán, Alex Wong, Ian Abraham

Depth perception models are typically trained on non-interactive datasets with predefined camera trajectories. However, this often introduces systematic biases into the learning process correlated to specific camera path…

Depth CompletionDepth EstimationMotion PlanningRobot Navigation+1

Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not

2021-12-13 · NeurIPS Workshop ICBINB 2021 12 · Chelsea Murray, James U. Allingham, Javier Antorán, José Miguel Hernández-Lobato

Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance. For overparameterised models such as NNs, however, correction leads either to …

Active Learning

ProbeMDE: Uncertainty-Guided Active Proprioception for Monocular Depth Estimation in Surgical Robotics

2025-12-12 · Britton Jordan, Jordan Thompson, Jesse F. d'Almeida, Hao Li 외 arxiv

Monocular depth estimation (MDE) provides a useful tool for robotic perception, but its predictions are often uncertain and inaccurate in challenging environments such as surgical scenes where textureless surfaces, specu…

Monocular Depth Estimation

Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera

2019-01-09 · Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa Narasimhan 외

Depth sensing is crucial for 3D reconstruction and scene understanding. Active depth sensors provide dense metric measurements, but often suffer from limitations such as restricted operating ranges, low spatial resolutio…

3D Reconstruction3D Scene ReconstructionScene Understanding

Neural RGB(r)D Sensing: Depth and Uncertainty From a Video Camera

2019-06-01 · CVPR 2019 6 · Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa G. Narasimhan 외

Depth sensing is crucial for 3D reconstruction and scene understanding. Active depth sensors provide dense metric measurements, but often suffer from limitations such as restricted operating ranges, low spatial resolutio…

3D Reconstruction3D Scene ReconstructionScene Understanding