Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
This addresses robustness issues in safety-critical systems like autonomous vehicles and healthcare, but it is incremental as it builds on self-supervised learning and graph techniques.
The paper tackled the problem of improving out-of-distribution detection in AI systems to enhance robustness, achieving an AUROC of 0.99 compared to state-of-the-art methods.
Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in safety-critical systems, such as autonomous vehicles, transportation, or healthcare, where malfunctions could have severe consequences. This paper proposes an approach to improve OOD detection without the need of labeled data, thereby increasing the AI systems' robustness. The proposed approach leverages the principles of self-supervised learning, allowing the model to learn useful representations from unlabeled data. Combined with graph-theoretical techniques, this enables the more efficient identification and categorization of OOD samples. Compared to existing state-of-the-art methods, this approach achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) = 0.99.