Cascading Unknown Detection with Known Classification for Open Set Recognition

TL;DR

This paper introduces Cas-DC, a cascading approach that separately learns functions for detecting unknowns and classifying knowns, significantly improving open set recognition performance.

Contribution

The paper proposes a novel cascading method, Cas-DC, that specializes functions for unknown detection and known class classification, outperforming existing methods.

Findings

Cas-DC achieves higher AUROC scores in open set recognition.

Cas-DC improves correct classification rates at various true positive rates.

Experimental results demonstrate superior performance over modern methods.

Abstract

Deep learners tend to perform well when trained under the closed set assumption but struggle when deployed under open set conditions. This motivates the field of Open Set Recognition in which we seek to give deep learners the ability to recognize whether a data sample belongs to the known classes trained on or comes from the surrounding infinite world. Existing open set recognition methods typically rely upon a single function for the dual task of distinguishing between knowns and unknowns as well as making known class distinction. This dual process leaves performance on the table as the function is not specialized for either task. In this work, we introduce Cascading Unknown Detection with Known Classification (Cas-DC), where we instead learn specialized functions in a cascading fashion for both known/unknown detection and fine class classification amongst the world of knowns. Our experiments and analysis demonstrate that Cas-DC handily outperforms modern methods in open set recognition when compared using AUROC scores and correct classification rate at various true positive rates.