SupLID: Geometrical Guidance for Out-of-Distribution Detection in Semantic Segmentation

TL;DR

SupLID introduces a geometrical approach using Linear Intrinsic Dimensionality to improve pixel-level out-of-distribution detection in semantic segmentation, achieving state-of-the-art results by complementing confidence-based scores.

Contribution

It presents a novel geometrical framework that guides OOD scores at the superpixel level, enhancing detection accuracy and efficiency in semantic segmentation.

Findings

Significantly improves OOD detection metrics such as AUR, FPR, and AUP.

Enables real-time inference with spatial smoothness.

Seamlessly integrates with existing segmentation models as a post-hoc method.

Abstract

Out-of-Distribution (OOD) detection in semantic segmentation aims to localize anomalous regions at the pixel level, advancing beyond traditional image-level OOD techniques to better suit real-world applications such as autonomous driving. Recent literature has successfully explored the adaptation of commonly used image-level OOD methods--primarily based on classifier-derived confidence scores (e.g., energy or entropy)--for this pixel-precise task. However, these methods inherit a set of limitations, including vulnerability to overconfidence. In this work, we introduce SupLID, a novel framework that effectively guides classifier-derived OOD scores by exploiting the geometrical structure of the underlying semantic space, particularly using Linear Intrinsic Dimensionality (LID). While LID effectively characterizes the local structure of high-dimensional data by analyzing distance distributions, its direct application at the pixel level remains challenging. To overcome this, SupLID constructs a geometrical coreset that captures the intrinsic structure of the in-distribution (ID) subspace. It then computes OOD scores at the superpixel level, enabling both efficient real-time inference and improved spatial smoothness. We demonstrate that geometrical cues derived from SupLID serve as a complementary signal to traditional classifier confidence, enhancing the model's ability to detect diverse OOD scenarios. Designed as a post-hoc scoring method, SupLID can be seamlessly integrated with any semantic segmentation classifier at deployment time. Our results demonstrate that SupLID significantly enhances existing classifier-based OOD scores, achieving state-of-the-art performance across key evaluation metrics, including AUR, FPR, and AUP. Code is available at https://github.com/hdnugit/SupLID.