We inspect the calibration properties of common detection networks and extend state-of-the-art recalibration methods. Our methods use a Gaussian process (GP) recalibration scheme that yields parametric distributions as output (e.g. Gaussian or Cauchy). The usage…
Segmentation-guided Domain Adaptation for Efficient Depth Completion
Complete depth information and efficient estimators have become vital ingredients in scene understanding for automated driving tasks. A major problem for LiDAR-based depth completion is the inefficient utilization of convolutions due to the lack of…
Confidence calibration for object detection and segmentation
Calibrated confidence estimates obtained from neural networks are crucial, particularly for safety-critical applications such as autonomous driving or medical image diagnosis. However, although the task of confidence calibration has been investigated on classification problems, thorough…
Towards Black-Box Explainability with Gaussian Discriminant Knowledge Distillation
In this paper, we propose a method for post-hoc ex- plainability of black-box models. The key component of the semantic and quantitative local explanation is a knowledge distillation (KD) process which is used to mimic…
Bayesian Confidence Calibration for Epistemic Uncertainty Modelling
Modern neural networks have found to be miscal- ibrated in terms of confidence calibration, i.e., their predicted confidence scores do not reflect the observed accuracy or precision. Recent work has introduced methods for post-hoc confidence…
From Black-box to White-box: Examining Confidence Calibration under different Conditions
Confidence calibration is a major concern when applying artificial neural networks in safety-critical applications. Since most research in this area has focused on classification in the past, confidence calibration in the scope of object detection…
Multivariate Confidence Calibration for Object Detection
Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates. Though there is a variety of methods for classification, the field of object…
Dependency Decomposition and a Reject Option for Explainable Models
Deploying machine learning models in safety-related domains (e.g. autonomous driving, medical diagnosis) demands for approaches that are explainable, robust against adversarial attacks and aware of the model uncertainty. Recent deep learning models perform extremely well…
Markov random field for image synthesis with an application to traffic sign recognition
In current state-of-the-art systems for object detection and classification a huge amount of data is needed. Even if large databases are available, some classes are typically underrepresented and therefore the classifier is not able to…