Norm-Scaling for Out-of-Distribution Detection
This addresses the issue of reliable deployment for AI systems by improving detection of anomalous inputs, though it is an incremental advance on existing threshold-based methods.
The paper tackled the problem of out-of-distribution detection in deep neural networks by proposing norm-scaling to normalize logits per class, achieving a 9.78% improvement in AUROC, 5.99% in AUPR, and 33.19% reduction in FPR95 over previous state-of-the-art methods.
Out-of-Distribution (OoD) inputs are examples that do not belong to the true underlying distribution of the dataset. Research has shown that deep neural nets make confident mispredictions on OoD inputs. Therefore, it is critical to identify OoD inputs for safe and reliable deployment of deep neural nets. Often a threshold is applied on a similarity score to detect OoD inputs. One such similarity is angular similarity which is the dot product of latent representation with the mean class representation. Angular similarity encodes uncertainty, for example, if the angular similarity is less, it is less certain that the input belongs to that class. However, we observe that, different classes have different distributions of angular similarity. Therefore, applying a single threshold for all classes is not ideal since the same similarity score represents different uncertainties for different classes. In this paper, we propose norm-scaling which normalizes the logits separately for each class. This ensures that a single value consistently represents similar uncertainty for various classes. We show that norm-scaling, when used with maximum softmax probability detector, achieves 9.78% improvement in AUROC, 5.99% improvement in AUPR and 33.19% reduction in FPR95 metrics over previous state-of-the-art methods.