Temp-SCONE: A Novel Out-of-Distribution Detection and Domain Generalization Framework for Wild Data with Temporal Shift

TL;DR

Temp-SCONE is a new framework extending SCONE to handle temporal shifts in dynamic environments, improving out-of-distribution detection and robustness in open-world learning scenarios.

Contribution

It introduces a confidence-driven regularization loss based on Average Thresholded Confidence to enhance temporal stability and generalization in dynamic environments.

Findings

Significantly improves robustness under temporal drift.

Achieves higher accuracy on dynamic datasets.

Maintains performance on datasets without temporal continuity.

Abstract

Open-world learning (OWL) requires models that can adapt to evolving environments while reliably detecting out-of-distribution (OOD) inputs. Existing approaches, such as SCONE, achieve robustness to covariate and semantic shifts but assume static environments, leading to degraded performance in dynamic domains. In this paper, we propose Temp-SCONE, a temporally consistent extension of SCONE designed to handle temporal shifts in dynamic environments. Temp-SCONE introduces a confidence-driven regularization loss based on Average Thresholded Confidence (ATC), penalizing instability in predictions across time steps while preserving SCONE's energy-margin separation. Experiments on dynamic datasets demonstrate that Temp-SCONE significantly improves robustness under temporal drift, yielding higher corrupted-data accuracy and more reliable OOD detection compared to SCONE. On distinct datasets without temporal continuity, Temp-SCONE maintains comparable performance, highlighting the importance and limitations of temporal regularization. Our theoretical insights on temporal stability and generalization error further establish Temp-SCONE as a step toward reliable OWL in evolving dynamic environments.