3 citations · 3 across the 2 of their papers we have counts for
5 papers
Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates
Alina Roitberg, Kunyu Peng, David Schneider +4
Driver observation models are rarely deployed under perfect conditions. In practice, illumination, camera placement and type differ from the ones present during training and unfore…
Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models
Alina Roitberg, Monica Haurilet, Manuel Martinez +1
Beyond assigning the correct class, an activity recognition model should also be able to determine, how certain it is in its predictions. We present the first study of how welthe c…
Detective: An Attentive Recurrent Model for Sparse Object Detection
Amine Kechaou, Manuel Martinez, Monica Haurilet +1
In this work, we present Detective - an attentive object detector that identifies objects in images in a sequential manner. Our network is based on an encoder-decoder architecture,…
Rice-Marlin Codes: Tiny and Efficient Variable-to-Fixed Codes
Manuel Martinez, Joan Serra-Sagristà
Marlin is a Variable-to-Fixed (VF) codec optimized for high decoding speed through the use of small sized dictionaries that fit in the L1 cache of most CPUs. While the size of Marl…
Taming the Cross Entropy Loss
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. However, unlike…