Operational Open-Set Recognition and PostMax Refinement

Open-Set Recognition (OSR) is a problem with mainly practical applications. However, recent evaluations have largely focused on small-scale data and tuning thresholds over the test set, which disregard the real-world operational needs of parameter selection. Thus, we revisit the original goals of OSR and propose a new evaluation metric, Operational Open-Set Accuracy (OOSA), which requires predicting an operationally relevant threshold from a validation set with known and a surrogate set with unknown samples, and then applying this threshold during testing. With this new measure in mind, we develop a large-scale evaluation protocol suited for operational scenarios. Additionally, we introduce the novel PostMax algorithm that performs post-processing refinement of the logit of the maximal class. This refinement involves normalizing logits by deep feature magnitudes and utilizing an extreme-value-based generalized Pareto distribution to map them into proper probabilities. We evaluate multiple pre-trained deep networks, including leading transformer and convolution-based architectures, on different selections of large-scale surrogate and test sets. Our experiments demonstrate that PostMax advances the state of the art in open-set recognition, showing statistically significant improvements in our novel OOSA metric as well as in previously used metrics such as AUROC, FPR95, and others.