# Labeling Neural Representations with Inverse Recognition

arXiv: https://arxiv.org/abs/2311.13594 · HTML: https://mlsanity.com/paper/2311.13594/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 75 references that are in the map.
- First posted on arXiv 22 Nov 2023.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [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)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques](https://mlsanity.com/paper/1909.03012/) (2019)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Analyzing Differentiable Fuzzy Logic Operators](https://mlsanity.com/paper/2002.06100/) (2020)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees](https://mlsanity.com/paper/2301.11911/) (2023)
- [Don't trust your eyes: on the (un)reliability of feature visualizations](https://mlsanity.com/paper/2306.04719/) (2023)

## Built on by (most cited first, 30 of 32)

- [Interpreting CLIP with Hierarchical Sparse Autoencoders](https://mlsanity.com/paper/2502.20578/) (2025)
- [PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits](https://mlsanity.com/paper/2404.06453/) (2024)
- [From Colors to Classes: Emergence of Concepts in Vision Transformers](https://mlsanity.com/paper/2503.24071/) (2025)
- [Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations](https://mlsanity.com/paper/2311.16681/) (2023)
- [Linear Explanations for Individual Neurons](https://mlsanity.com/paper/2405.06855/) (2024)
- [CoSy: Evaluating Textual Explanations of Neurons](https://mlsanity.com/paper/2405.20331/) (2024)
- [FADE: Why Bad Descriptions Happen to Good Features](https://mlsanity.com/paper/2502.16994/) (2025)
- [Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework](https://mlsanity.com/paper/2506.15538/) (2025)
- [Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features](https://mlsanity.com/paper/2408.17198/) (2024)
- [LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions](https://mlsanity.com/paper/2406.08572/) (2024)
- [LaVCa: LLM-assisted Visual Cortex Captioning](https://mlsanity.com/paper/2502.13606/) (2025)
- [Evaluating Neuron Explanations: A Unified Framework with Sanity Checks](https://mlsanity.com/paper/2506.05774/) (2025)
- [Manipulating Feature Visualizations with Gradient Slingshots](https://mlsanity.com/paper/2401.06122/) (2024)
- [NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions](https://mlsanity.com/paper/2502.16105/) (2025)
- [Deciphering Functions of Neurons in Vision-Language Models](https://mlsanity.com/paper/2502.18485/) (2025)
- [Interpreting Language Models Through Concept Descriptions: A Survey](https://mlsanity.com/paper/2510.01048/) (2025)
- [Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability](https://mlsanity.com/paper/2512.18092/) (2025)
- [Towards Utilising a Range of Neural Activations for Comprehending Representational Associations](https://mlsanity.com/paper/2411.10019/) (2024)
- [Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning](https://mlsanity.com/paper/2501.05205/) (2025)
- [Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data](https://mlsanity.com/paper/2501.13818/) (2025)
- [Data Science Principles for Interpretable and Explainable AI](https://mlsanity.com/paper/2405.10552/) (2024)
- [SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders](https://mlsanity.com/paper/2605.06610/) (2026)
- [Characterization of topological structures in different neural network architectures](https://mlsanity.com/paper/2407.06286/) (2024)
- [Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability](https://mlsanity.com/paper/2506.07985/) (2025)
- [TRANSPORTER: Transferring Visual Semantics from VLM Manifolds](https://mlsanity.com/paper/2511.18359/) (2025)
- [Open Vocabulary Compositional Explanations for Neuron Alignment](https://mlsanity.com/paper/2511.20931/) (2025)
- [Guaranteed Optimal Compositional Explanations for Neurons](https://mlsanity.com/paper/2511.20934/) (2025)
- [LINE: LLM-based Iterative Neuron Explanations for Vision Models](https://mlsanity.com/paper/2604.08039/) (2026)
- [Concept-wise Attention for Fine-grained Concept Bottleneck Models](https://mlsanity.com/paper/2604.15748/) (2026)
- [Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples](https://mlsanity.com/paper/2604.22477/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown. Existing global explainability methods, such as Network Dissection, face limitations such as reliance on segmentation masks, lack of statistical significance testing, and high computational demands. We propose Inverse Recognition (INVERT), a scalable approach for connecting learned representations with human-understandable concepts by leveraging their capacity to discriminate between these concepts. In contrast to prior work, INVERT is capable of handling diverse types of neurons, exhibits less computational complexity, and does not rely on the availability of segmentation masks. Moreover, INVERT provides an interpretable metric assessing the alignment between the representation and its corresponding explanation and delivering a measure of statistical significance. We demonstrate the applicability of INVERT in various scenarios, including the identification of representations affected by spurious correlations, and the interpretation of the hierarchical structure of decision-making within the models.