Improving Entropic Out-of-Distribution Detection using Isometric Distances and the Minimum Distance Score

David Macêdo, Teresa Ludermir

Keywords: Out-of-distribution detection

Abstract: Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (classification accuracy drop and slow/inefficient inferences). Recently, entropic out-of-distribution detection has been proposed as a seamless approach (i.e., a solution that avoids all the previously mentioned drawbacks). The entropic out-of-distribution detection solution comprises the IsoMax loss for training and the entropic score for out-of-distribution detection. The IsoMax loss works as a SoftMax loss drop-in replacement because swapping the SoftMax loss with the IsoMax loss requires no changes in the model's architecture or training procedures/hyperparameters. In this paper, we propose to perform what we call an isometrization of the distances used in the IsoMax loss. Additionally, we propose to replace the entropic score with the minimum distance score. Our experiments showed that these simple modifications increase out-of-distribution detection performance while keeping the solution seamless.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: We improved the performance of the entropic out-of-distribution detection approach keeping the solution seamless by performing what we call distance isometrization and using a score based on minimum distance.

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/improving-entropic-out-of-distribution/code)