# Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output

arXiv: https://arxiv.org/abs/1910.10307 · HTML: https://mlsanity.com/paper/1910.10307/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2019.

## Built on by (most cited first, 20 of 20)

- [MOOD: Multi-level Out-of-distribution Detection](https://mlsanity.com/paper/2104.14726/) (2021)
- [Neural Mean Discrepancy for Efficient Out-of-Distribution Detection](https://mlsanity.com/paper/2104.11408/) (2021)
- [SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection](https://mlsanity.com/paper/2208.13930/) (2022)
- [Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning](https://mlsanity.com/paper/2405.14039/) (2024)
- [Out-of-Distribution Detection for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2209.14435/) (2022)
- [EAT: Towards Long-Tailed Out-of-Distribution Detection](https://mlsanity.com/paper/2312.08939/) (2023)
- [Out-of-distribution Detection with Boundary Aware Learning](https://mlsanity.com/paper/2112.11648/) (2021)
- [A Uniform Framework for Anomaly Detection in Deep Neural Networks](https://mlsanity.com/paper/2110.03092/) (2021)
- [Layer Adaptive Deep Neural Networks for Out-of-distribution Detection](https://mlsanity.com/paper/2203.00192/) (2022)
- [Proto-OOD: Enhancing OOD Object Detection with Prototype Feature Similarity](https://mlsanity.com/paper/2409.05466/) (2024)
- [Rule-based Out-Of-Distribution Detection](https://mlsanity.com/paper/2303.01860/) (2023)
- [Anomaly Detection with Test Time Augmentation and Consistency Evaluation](https://mlsanity.com/paper/2206.02345/) (2022)
- [Toward a Realistic Benchmark for Out-of-Distribution Detection](https://mlsanity.com/paper/2404.10474/) (2024)
- [DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions](https://mlsanity.com/paper/2109.13237/) (2021)
- [Detecting Unknown DGAs without Context Information](https://mlsanity.com/paper/2205.14940/) (2022)
- [Interpreting deep learning output for out-of-distribution detection](https://mlsanity.com/paper/2211.03637/) (2022)
- [A Multi-Scale Framework for Out-of-Distribution Detection in Dermoscopic Images](https://mlsanity.com/paper/2301.07533/) (2023)
- [On the Detection of Anomalous or Out-Of-Distribution Data in Vision Models Using Statistical Techniques](https://mlsanity.com/paper/2403.15497/) (2024)
- [Anomaly Detection Based on Critical Paths for Deep Neural Networks](https://mlsanity.com/paper/2505.14967/) (2025)
- [Geometric Collapse: When Vision Models Fail to Verify Physical Causality](https://mlsanity.com/paper/2607.06871/) (2026)

## Abstract (arXiv)

Deep neural networks achieve superior performance in challenging tasks such as image classification. However, deep classifiers tend to incorrectly classify out-of-distribution (OOD) inputs, which are inputs that do not belong to the classifier training distribution. Several approaches have been proposed to detect OOD inputs, but the detection task is still an ongoing challenge. In this paper, we propose a new OOD detection approach that can be easily applied to an existing classifier and does not need to have access to OOD samples. The detector is a one-class classifier trained on the output of an early layer of the original classifier fed with its original training set. We apply our approach to several low- and high-dimensional datasets and compare it to the state-of-the-art detection approaches. Our approach achieves substantially better results over multiple metrics.