Logit Scaling for Out-of-Distribution Detection

TL;DR

This paper introduces Logit Scaling (LTS), a simple post-hoc method for out-of-distribution detection that does not require retraining or access to training data, demonstrating state-of-the-art results across multiple datasets and architectures.

Contribution

Proposes Logit Scaling (LTS), a novel post-hoc OOD detection technique that maintains high performance without retraining or training data access, applicable across various architectures.

Findings

Achieves state-of-the-art OOD detection performance

Demonstrates robustness across multiple datasets and architectures

Maintains effectiveness without retraining or data access

Abstract

The safe deployment of machine learning and AI models in open-world settings hinges critically on the ability to detect out-of-distribution (OOD) data accurately, data samples that contrast vastly from what the model was trained with. Current approaches to OOD detection often require further training the model, and/or statistics about the training data which may no longer be accessible. Additionally, many existing OOD detection methods struggle to maintain performance when transferred across different architectures. Our research tackles these issues by proposing a simple, post-hoc method that does not require access to the training data distribution, keeps a trained network intact, and holds strong performance across a variety of architectures. Our method, Logit Scaling (LTS), as the name suggests, simply scales the logits in a manner that effectively distinguishes between in-distribution (ID) and OOD samples. We tested our method on benchmarks across various scales, including CIFAR-10, CIFAR-100, ImageNet and OpenOOD. The experiments cover 3 ID and 14 OOD datasets, as well as 9 model architectures. Overall, we demonstrate state-of-the-art performance, robustness and adaptability across different architectures, paving the way towards a universally applicable solution for advanced OOD detection.