Papers › Improving Confident-Classifiers For Out-of-distribution Detection
Improving Confident-Classifiers For Out-of-distribution Detection
Sachin Vernekar, Ashish Gaurav, Vahdat Abdelzad, Taylor Denouden, Rick Salay, Krzysztof Czarnecki
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 KLdivergence between the predictive distribution of OOD samples in the low-density“boundary” 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 also propose a novel algorithm to generate the“boundary” OOD samples to train a classifier with an explicit “reject” class for OOD samples. We compare our approach against several recent classifier-based OOD detectors including the confident-classifiers on MNIST and Fashion-MNISTdatasets. Overall the proposed approach consistently performs better than others across most of the experiments.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections