Skip to content
Book Open access

When Models Leave the Training Distribution: A Tutorial on OOD Detection

Aug 2026 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · 0 citations · 35 references

TL;DR

This tutorial covers recent developments in OOD detection from both theoretical and practical perspectives, including four major categories: (1) post-hoc methods, (2) training-based methods with auxiliary outliers, (3) training methods without auxiliary outliers, and (4) foundation model-based approaches, along with recent advances in each area.

Abstract

Despite their remarkable success, Deep Neural Networks (DNNs) remain challenging to deploy in critical applications due to their inability to handle out-of-distribution (OOD) data. DNNs are trained assuming training and deployment data follow the same distribution, but this assumption is often violated in practice. When encountering unfamiliar inputs, models may produce highly confident yet incorrect predictions, and in high-stakes decision-making environments, such incorrect predictions can be costly. OOD detection has thus become fundamental across deep learning, affecting applications from computer vision and NLP to security, autonomous systems, and generative models. This tutorial covers recent developments in OOD detection from both theoretical and practical perspectives, including four major categories: (1) post-hoc methods, (2) training-based methods with auxiliary outliers, (3) training methods without auxiliary outliers, and (4) foundation model-based approaches, along with recent advances in each area.

Read PDF

Similar papers

Preprint Jul 2026

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

A novel approach that leverages sparse autoencoders (SAEs) to learn interpretable features from these intermediate activations and proposes a new OOD score derived from the cosine similarity between the sparse feature activations of a test sample and the mean activations of ID classes.

Ayush Karmacharya, Luke Luschwitz, Lucia Romero et al. · 0 citations
Review Jul 2026

Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

This comprehensive survey formally defines the CTTA problem, analyzes the diverse continual domain shift patterns that characterize different evaluation protocols, and proposes a hierarchical taxonomy that categorizes existing methods into three families: optimization-based strategies (entropy minimization, pseudo-labeling, parameter restoration), parameter-efficient methods (normalization layer adaptation, adaptive parameter selection), and architecture-based approaches (teacher-student frameworks, adapters, visual prompting, masked modeling).

Sarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang et al. · 2 citations

Transferring Deep Learning Technology to Industry

The findings demonstrate that introducing prior structure, through strategic sparse supervision, pre-trained multimodal knowledge, or transferable representations, consistently compensates for limited labeled data across diverse vision tasks.

Tobias Schiele · 0 citations
Preprint Aug 2026

MuST-VAD: Mutual Structured Learning for Video Anomaly Detection

In this paper, we propose MuST-VAD, a mutual structured learning framework for weakly supervised video anomaly detection (VAD) in which an anomaly detector and a large vision-language model (LVLM) exchange their acquired knowledge. Detectors in weakly supervised VAD learn anomaly scores from features extracted by a fixed, task-agnostic backbone. These fixed features bound the achievable detection accuracy. Recent methods therefore transfer LVLM semantics into the detector as richer features. However, this transfer is one-way: what the detector learns about the target videos never returns to the LVLM. MuST-VAD extends the one-way transfer into a bidirectional learning loop. In this loop, the latest detector predictions supervise the LVLM adaptation, and the adapted LVLM returns updated representations that retrain the detector; the two models alternate these updates over small video groups. Both models train on detector-selected key clips, while confidence weighting and annotation-anchored question answering keep the exchanged supervision reliable. On UCF-Crime, our mutual learning improves the one-pass transfer baseline from 88.15% to 88.63% AUROC and from 37.25% to 42.46% average precision (AP), outperforming the state-of-the-art method in AP by 4.13 points.

Satoshi Hashimoto, Hitoshi Nishimura, Mori Kurokawa · 0 citations
2025

X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection

A straightforward feature mixing approach for pre-trained Transformers is presented, which combines multi-layer representations via calculated importance weights, and identifies OOD samples using Mahalanobis distance in the blended feature space.

Tong Wei, Bolin Wang, Jiang-Xin Shi et al. · 8 citations · ⚡2