# Analysis of Confident-Classifiers for Out-of-distribution Detection

Source: [Analysis of Confident-Classifiers for Out-of-distribution Detection](<https://www.sota2.com/research/paper/68fa65a61e209131cea0b98a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:38.698Z

Authors: Sachin Vernekar, Ashish Gaurav, Taylor Denouden, Buu Phan, Vahdat Abdelzad, Rick Salay, Krzysztof Czarnecki

Published: 2019-04-27T22:33:34.000Z

## Abstract

Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called "confident-classifier" by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KL divergence between the predictive distribution of OOD samples in the low-density regions of in-distribution and the uniform distribution (maximizing the entropy of the outputs). Thus, the samples could be detected as OOD if they have low confidence or high entropy. In this paper, we analyze this setting both theoretically and experimentally. We conclude that the resulting confident-classifier still yields arbitrarily high confidence for OOD samples far away from the in-distribution. We instead suggest training a classifier by adding an explicit "reject" class for OOD samples.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1904.12220>)

[PDF](<https://arxiv.org/pdf/1904.12220.pdf>)
