kontakt@camo.nrw +49 202 / 439 1164

[Paper] Towards Black-Box Explainability with Gaussian Discriminant Knowledge Distillation

SAIAD 2021

In this paper, we propose a method for post-hoc explainability 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 the teacher’s behavior by means of an explainable generative model. Therefore, we introduce a Concept Probability Density Encoder (CPDE) in conjunction with a Gaussian Discriminant Decoder (GDD) to describe the contribution of high-level concepts (e.g. object parts, color, shape). We argue that our objective function encourages both, an explanation given by a set of likelihood ratios and a measure to describe how far the explainer deviates from the training data distribution of the concepts. The method can leverage any pre-trained concept classifier that admits concept scores (e.g. logits) or probabilities. We demonstrate the effectiveness of the proposed method in the context of object detection utilizing the DensePose dataset.

https://www.sites.google.com/view/saiad2021/home

Verwandte Arbeiten

[Paper] A Wizard of Oz Field Study to Understand Non-Driving-Related Activities, Trust, and Acceptance of Automated Vehicles

Understanding user needs and behavior in automated vehicles (AVs) while traveling is essential for future in-vehicle interface and service design. Since AVs are not yet market-ready, current knowledge about AV use and perception is based […]

Mehr erfahren

[Paper] 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 […]

Mehr erfahren

[Paper] “Help, Accident Ahead!”: Using Mixed Reality Environments in Automated Vehicles to Support Occupants After Passive Accident Experiences

Currently, car assistant systems mainly try to prevent accidents. Increasing built-in car technology also extends the potential applications in vehicles. Future cars might have virtual windshields that augment the traffic or individual virtual assistants interacting […]

Mehr erfahren