Deep Learning Uncertainty using Self-Supervised Learning
||Deep Learning Uncertainty using Self-Supervised Learning|
||Per Sidén <firstname.lastname@example.org>|
||2021-12-01 – 2022-06-01|
Deep learning uncertainty has been shown to greatly benefit from distance awareness. Spectral-normalized Neural Gaussian Process (SNGP, ) demonstrated that a deep neural network with distance awareness through spectral normalization combined with a distance-aware Gaussian process output layer can lead to high-quality uncertainty estimates using a single deterministic network. This could have large implications for safety-critical real-time applications in need of robust uncertainty predictions such as e.g. autonomous vehicles. However, the theoretical foundation for distance-awareness via spectral normalization has some flaws, and in this project we instead propose to investigate the potential of achieving distance awareness through self-supervised learning methods.
 Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness (https://arxiv.org/abs/2006.10108)