Synergistic Classification and Unknown Discrimination for Open Set Recognition
Keywords: Open Set Recognition, Open Set Classifier, Novelty Detection, Unknown Class Detection, Out-of-Distribution Detection
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 fine 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 Synergistic Classification and unknown Discrimination (SCAD), where we instead learn specialized functions for both known/unknown discrimination and fine class distinction amongst the world of knowns. Our experiments and analysis demonstrate that SCAD handily outperforms modern methods in open set recognition when compared using AUROC scores and correct classification rate at various true positive rates.
Primary Area: general machine learning (i.e., none of the above)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 2144
Loading