# DORA: Exploring Outlier Representations in Deep Neural Networks

arXiv: https://arxiv.org/abs/2206.04530 · HTML: https://mlsanity.com/paper/2206.04530/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 75 of its 180 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 30 of 75)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)

## Built on by (most cited first, 14 of 14)

- [Labeling Neural Representations with Inverse Recognition](https://mlsanity.com/paper/2311.13594/) (2023)
- [PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits](https://mlsanity.com/paper/2404.06453/) (2024)
- [Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science](https://mlsanity.com/paper/2303.00652/) (2023)
- [Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces](https://mlsanity.com/paper/2212.14855/) (2022)
- [Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations](https://mlsanity.com/paper/2311.16681/) (2023)
- [CoSy: Evaluating Textual Explanations of Neurons](https://mlsanity.com/paper/2405.20331/) (2024)
- [Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework](https://mlsanity.com/paper/2506.15538/) (2025)
- [Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks](https://mlsanity.com/paper/2304.05727/) (2023)
- [Manipulating Feature Visualizations with Gradient Slingshots](https://mlsanity.com/paper/2401.06122/) (2024)
- [Federated Learning over Connected Modes](https://mlsanity.com/paper/2403.03333/) (2024)
- [Atlas-Alignment: Making Interpretability Transferable Across Language Models](https://mlsanity.com/paper/2510.27413/) (2025)
- [Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data](https://mlsanity.com/paper/2501.13818/) (2025)
- [Characterization of topological structures in different neural network architectures](https://mlsanity.com/paper/2407.06286/) (2024)
- [When Multi-Sensor Fusion Fails to Generalize: Cattle Posture Classification Under Animal-Level and Temporal Distribution Shift](https://mlsanity.com/paper/2606.24986/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) excel at learning complex abstractions within their internal representations. However, the concepts they learn remain opaque, a problem that becomes particularly acute when models unintentionally learn spurious correlations. In this work, we present DORA (Data-agnOstic Representation Analysis), the first data-agnostic framework for analyzing the representational space of DNNs. Central to our framework is the proposed Extreme-Activation (EA) distance measure, which assesses similarities between representations by analyzing their activation patterns on data points that cause the highest level of activation. As spurious correlations often manifest in features of data that are anomalous to the desired task, such as watermarks or artifacts, we demonstrate that internal representations capable of detecting such artifactual concepts can be found by analyzing relationships within neural representations. We validate the EA metric quantitatively, demonstrating its effectiveness both in controlled scenarios and real-world applications. Finally, we provide practical examples from popular Computer Vision models to illustrate that representations identified as outliers using the EA metric often correspond to undesired and spurious concepts.