no code implementations • 10 Apr 2022 • Alina Roitberg, Kunyu Peng, David Schneider, Kailun Yang, Marios Koulakis, Manuel Martinez, Rainer Stiefelhagen
In this work, we for the first time examine how well the confidence values of modern driver observation models indeed match the probability of the correct outcome and show that raw neural network-based approaches tend to significantly overestimate their prediction quality.
no code implementations • 2 Jan 2021 • Alina Roitberg, Monica Haurilet, Manuel Martinez, Rainer Stiefelhagen
While temperature scaling alone drastically improves the reliability of the confidence values, our CARING method consistently leads to the best uncertainty estimates in all benchmark settings.
no code implementations • 25 Apr 2020 • Amine Kechaou, Manuel Martinez, Monica Haurilet, Rainer Stiefelhagen
At each iteration, our decoder focuses on the relevant parts of the image using an attention mechanism, and then estimates the object's class and the bounding box coordinates.
no code implementations • 11 Oct 2018 • Manuel Martinez, Rainer Stiefelhagen
We present the Tamed Cross Entropy (TCE) loss function, a robust derivative of the standard Cross Entropy (CE) loss used in deep learning for classification tasks.
no code implementations • 22 Nov 2016 • Manuel Martinez, Monica Haurilet, Ziad Al-Halah, Makarand Tapaswi, Rainer Stiefelhagen
The Earth Mover's Distance (EMD) computes the optimal cost of transforming one distribution into another, given a known transport metric between them.