Search Results for author:
Found 8 papers, 4 papers with code
Deep Active Learning with Noisy Oracle in Object Detection
Here, we propose a composite active learning framework including a label review module for deep object detection.
LMD: Light-weight Prediction Quality Estimation for Object Detection in Lidar Point Clouds
In order to address these two issues, we propose LidarMetaDetect (LMD), a light-weight post-processing scheme for prediction quality estimation.
Identifying Label Errors in Object Detection Datasets by Loss Inspection
In this work, we for the first time introduce a benchmark for label error detection methods on object detection datasets as well as a label error detection method and a number of baselines.
Towards Rapid Prototyping and Comparability in Active Learning for Deep Object Detection
Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire.
Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning
Training deep neural networks is already resource demanding and so is also their uncertainty quantification.
Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors
The vast majority of uncertainty quantification methods for deep object detectors such as variational inference are based on the network output.
MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection
On the other hand, meta regression gives rise to a quality estimate.
Uncertainty Measures and Prediction Quality Rating for the Semantic Segmentation of Nested Multi Resolution Street Scene Images
For the task of meta classification we obtain a classification accuracy of $81. 93\%$ and an AUROC of $89. 89\%$.
