On the Importance of Regularisation & Auxiliary Information in OOD Detection
This addresses a critical flaw in neural networks for applications like self-driving cars and finance, though it appears incremental as it builds on existing OOD detection methods.
The paper tackles the problem of neural networks making overconfident predictions for ambiguous inputs by introducing two novel objectives to improve out-of-distribution detection, empirically showing they outperform baselines and most existing approaches while maintaining competitive performance.
Neural networks are often utilised in critical domain applications (e.g. self-driving cars, financial markets, and aerospace engineering), even though they exhibit overconfident predictions for ambiguous inputs. This deficiency demonstrates a fundamental flaw indicating that neural networks often overfit on spurious correlations. To address this problem in this work we present two novel objectives that improve the ability of a network to detect out-of-distribution samples and therefore avoid overconfident predictions for ambiguous inputs. We empirically demonstrate that our methods outperform the baseline and perform better than the majority of existing approaches while still maintaining a competitive performance against the rest. Additionally, we empirically demonstrate the robustness of our approach against common corruptions and demonstrate the importance of regularisation and auxiliary information in out-of-distribution detection.