# Detecting semantic anomalies

arXiv: https://arxiv.org/abs/1908.04388 · HTML: https://mlsanity.com/paper/1908.04388/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2019.

## Built on by (most cited first, 30 of 50)

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [A Unified Model for Multi-class Anomaly Detection](https://mlsanity.com/paper/2206.03687/) (2022)
- [OpenOOD: Benchmarking Generalized Out-of-Distribution Detection](https://mlsanity.com/paper/2210.07242/) (2022)
- [OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.09301/) (2023)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [Mean-Shifted Contrastive Loss for Anomaly Detection](https://mlsanity.com/paper/2106.03844/) (2021)
- [Types of Out-of-Distribution Texts and How to Detect Them](https://mlsanity.com/paper/2109.06827/) (2021)
- [Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments](https://mlsanity.com/paper/2106.03917/) (2021)
- [A Closer Look at AUROC and AUPRC under Class Imbalance](https://mlsanity.com/paper/2401.06091/) (2024)
- [A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification](https://mlsanity.com/paper/2211.15259/) (2022)
- [Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images](https://mlsanity.com/paper/2205.11474/) (2022)
- [On the Out-of-distribution Generalization of Probabilistic Image Modelling](https://mlsanity.com/paper/2109.02639/) (2021)
- [No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets](https://mlsanity.com/paper/2109.05554/) (2021)
- [Transformaly -- Two (Feature Spaces) Are Better Than One](https://mlsanity.com/paper/2112.04185/) (2021)
- [Out-of-distribution Detection in Medical Image Analysis: A survey](https://mlsanity.com/paper/2404.18279/) (2024)
- [CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issue](https://mlsanity.com/paper/2108.06024/) (2021)
- [Looking 3D: Anomaly Detection with 2D-3D Alignment](https://mlsanity.com/paper/2406.19393/) (2024)
- [Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features](https://mlsanity.com/paper/2301.12715/) (2023)
- [Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations](https://mlsanity.com/paper/2108.04116/) (2021)
- [Fine-grain Inference on Out-of-Distribution Data with Hierarchical Classification](https://mlsanity.com/paper/2209.04493/) (2022)
- [Anomaly Detection Based on Isolation Mechanisms: A Survey](https://mlsanity.com/paper/2403.10802/) (2024)
- [No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detection](https://mlsanity.com/paper/2306.07284/) (2023)
- [READ: Aggregating Reconstruction Error into Out-of-distribution Detection](https://mlsanity.com/paper/2206.07459/) (2022)
- [When and How Does In-Distribution Label Help Out-of-Distribution Detection?](https://mlsanity.com/paper/2405.18635/) (2024)
- [Data Invariants to Understand Unsupervised Out-of-Distribution Detection](https://mlsanity.com/paper/2111.13362/) (2021)
- [GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection](https://mlsanity.com/paper/2510.17131/) (2025)
- [Odd-One-Out: Anomaly Detection by Comparing with Neighbors](https://mlsanity.com/paper/2406.20099/) (2024)
- [Multi-Class Anomaly Detection](https://mlsanity.com/paper/2110.15108/) (2021)
- [TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring](https://mlsanity.com/paper/2207.11290/) (2022)
- [Beyond Mahalanobis-Based Scores for Textual OOD Detection](https://mlsanity.com/paper/2211.13527/) (2022)

## Abstract (arXiv)

We critically appraise the recent interest in out-of-distribution (OOD) detection and question the practical relevance of existing benchmarks. While the currently prevalent trend is to consider different datasets as OOD, we argue that out-distributions of practical interest are ones where the distinction is semantic in nature for a specified context, and that evaluative tasks should reflect this more closely. Assuming a context of object recognition, we recommend a set of benchmarks, motivated by practical applications. We make progress on these benchmarks by exploring a multi-task learning based approach, showing that auxiliary objectives for improved semantic awareness result in improved semantic anomaly detection, with accompanying generalization benefits.