# The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods

arXiv: https://arxiv.org/abs/2203.02486 · HTML: https://mlsanity.com/paper/2203.02486/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 4 Mar 2022.

## Builds on (most cited first, 17 of 17)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [fastai: A Layered API for Deep Learning](https://mlsanity.com/paper/2002.04688/) (2020)
- [Adversarial Reciprocal Points Learning for Open Set Recognition](https://mlsanity.com/paper/2103.00953/) (2021)
- [Hybrid Models for Open Set Recognition](https://mlsanity.com/paper/2003.12506/) (2020)
- [Feature Space Singularity for Out-of-Distribution Detection](https://mlsanity.com/paper/2011.14654/) (2020)
- [From Heatmaps to Structural Explanations of Image Classifiers](https://mlsanity.com/paper/2109.06365/) (2021)

## Built on by (most cited first, 28 of 28)

- [OpenMix: Exploring Outlier Samples for Misclassification Detection](https://mlsanity.com/paper/2303.17093/) (2023)
- [Understanding the Feature Norm for Out-of-Distribution Detection](https://mlsanity.com/paper/2310.05316/) (2023)
- [Towards Better Selective Classification](https://mlsanity.com/paper/2206.09034/) (2022)
- [Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection](https://mlsanity.com/paper/2402.00865/) (2024)
- [Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks](https://mlsanity.com/paper/2408.16757/) (2024)
- [Measuring Human Perception to Improve Open Set Recognition](https://mlsanity.com/paper/2209.03519/) (2022)
- [Embrace Limited and Imperfect Training Datasets: Opportunities and Challenges in Plant Disease Recognition Using Deep Learning](https://mlsanity.com/paper/2305.11533/) (2023)
- [Oracle Analysis of Representations for Deep Open Set Detection](https://mlsanity.com/paper/2209.11350/) (2022)
- [A Domain-Independent Agent Architecture for Adaptive Operation in Evolving Open Worlds](https://mlsanity.com/paper/2306.06272/) (2023)
- [All Beings Are Equal in Open Set Recognition](https://mlsanity.com/paper/2401.17654/) (2024)
- [Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models](https://mlsanity.com/paper/2411.17767/) (2024)
- [Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space](https://mlsanity.com/paper/2207.07710/) (2022)
- [Understanding Open-Set Recognition by Jacobian Norm and Inter-Class Separation](https://mlsanity.com/paper/2209.11436/) (2022)
- [Hidden Conflicts in Neural Networks and Their Implications for Explainability](https://mlsanity.com/paper/2310.20363/) (2023)
- [HiNoVa: A Novel Open-Set Detection Method for Automating RF Device Authentication](https://mlsanity.com/paper/2305.09594/) (2023)
- [Deep Neural Networks Tend To Extrapolate Predictably](https://mlsanity.com/paper/2310.00873/) (2023)
- [SphOR: A Representation Learning Perspective on Open-set Recognition for Identifying Unknown Classes in Deep Learning Models](https://mlsanity.com/paper/2503.08049/) (2025)
- [Beyond Deepfake vs Real: Facial Deepfake Detection in the Open-Set Paradigm](https://mlsanity.com/paper/2503.08055/) (2025)
- [Data-Centric Governance](https://mlsanity.com/paper/2302.07872/) (2023)
- [Don't Miss Out on Novelty: Importance of Novel Features for Deep Anomaly Detection](https://mlsanity.com/paper/2310.00797/) (2023)
- [Familiarity-Based Open-Set Recognition Under Adversarial Attacks](https://mlsanity.com/paper/2311.05006/) (2023)
- [Towards Open-set Gesture Recognition via Feature Activation Enhancement and Orthogonal Prototype Learning](https://mlsanity.com/paper/2312.02535/) (2023)
- [Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition](https://mlsanity.com/paper/2404.10370/) (2024)
- [Dimensionality-induced information loss of outliers in deep neural networks](https://mlsanity.com/paper/2410.21656/) (2024)
- [Boosting Open Set Recognition Performance through Modulated Representation Learning](https://mlsanity.com/paper/2505.18137/) (2025)
- [COSTARR: Consolidated Open Set Technique with Attenuation for Robust Recognition](https://mlsanity.com/paper/2508.01087/) (2025)
- [Foundation Models are Implicit Deepfake Detectors](https://mlsanity.com/paper/2608.09427/) (2026)
- [SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing](https://mlsanity.com/paper/2610.00851/) (2026)

## Abstract (arXiv)

In many object recognition applications, the set of possible categories is an open set, and the deployed recognition system will encounter novel objects belonging to categories unseen during training. Detecting such "novel category" objects is usually formulated as an anomaly detection problem. Anomaly detection algorithms for feature-vector data identify anomalies as outliers, but outlier detection has not worked well in deep learning. Instead, methods based on the computed logits of visual object classifiers give state-of-the-art performance. This paper proposes the Familiarity Hypothesis that these methods succeed because they are detecting the absence of familiar learned features rather than the presence of novelty. This distinction is important, because familiarity-based detection will fail in many situations where novelty is present. For example when an image contains both a novel object and a familiar one, the familiarity score will be high, so the novel object will not be noticed. The paper reviews evidence from the literature and presents additional evidence from our own experiments that provide strong support for this hypothesis. The paper concludes with a discussion of whether familiarity-based detection is an inevitable consequence of representation learning.