COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification

2026-02-04

SDM

AI Summary

This work addresses the challenge of effectively detecting near-distribution out-of-distribution (near-OOD) samples in image classification inference, a task where existing methods often fall short. To this end, the authors propose COMBOOD, an unsupervised semi-parametric framework that uniquely integrates non-parametric nearest-neighbor distances with parametric Mahalanobis distances in the feature embedding space to produce a unified confidence score. This fusion enables robust performance across both near-OOD and far-OOD scenarios. COMBOOD is compatible with diverse feature extractors and exhibits computational complexity that scales linearly with the embedding dimensionality. Extensive evaluations on OpenOOD v1/v1.5 benchmarks and document datasets demonstrate that COMBOOD consistently outperforms current state-of-the-art methods, with most improvements achieving statistical significance.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Identifying out-of-distribution (OOD) data at inference time is crucial for many machine learning applications, especially for automation. We present a novel unsupervised semi-parametric framework COMBOOD for OOD detection with respect to image recognition. Our framework combines signals from two distance metrics, nearest-neighbor and Mahalanobis, to derive a confidence score for an inference point to be out-of-distribution. The former provides a non-parametric approach to OOD detection. The latter provides a parametric, simple, yet effective method for detecting OOD data points, especially, in the far OOD scenario, where the inference point is far apart from the training data set in the embedding space. However, its performance is not satisfactory in the near OOD scenarios that arise in practical situations. Our COMBOOD framework combines the two signals in a semi-parametric setting to provide a confidence score that is accurate both for the near-OOD and far-OOD scenarios. We show experimental results with the COMBOOD framework for different types of feature extraction strategies. We demonstrate experimentally that COMBOOD outperforms state-of-the-art OOD detection methods on the OpenOOD (both version 1 and most recent version 1.5) benchmark datasets (for both far-OOD and near-OOD) as well as on the documents dataset in terms of accuracy. On a majority of the benchmark datasets, the improvements in accuracy resulting from the COMBOOD framework are statistically significant. COMBOOD scales linearly with the size of the embedding space, making it ideal for many real-life applications.

Problem

• out-of-distribution detection
• image classification
• near-OOD
• far-OOD
• inference-time uncertainty

Innovation

• semi-parametric
• out-of-distribution detection
• Mahalanobis distance
• nearest-neighbor
• image classification