# Understanding Intra-Class Knowledge Inside CNN

arXiv: https://arxiv.org/abs/1507.02379 · HTML: https://mlsanity.com/paper/1507.02379/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2015.

## Built on by (most cited first, 22 of 22)

- [Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization](https://mlsanity.com/paper/2306.06805/) (2023)
- [Refining activation downsampling with SoftPool](https://mlsanity.com/paper/2101.00440/) (2021)
- [Detecting when pre-trained nnU-Net models fail silently for Covid-19 lung lesion segmentation](https://mlsanity.com/paper/2107.05975/) (2021)
- [Explainable Machine Learning with Prior Knowledge: An Overview](https://mlsanity.com/paper/2105.10172/) (2021)
- [Experimental Observations of the Topology of Convolutional Neural Network Activations](https://mlsanity.com/paper/2212.00222/) (2022)
- [Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools](https://mlsanity.com/paper/2110.07120/) (2021)
- [Visualizing Global Explanations of Point Cloud DNNs](https://mlsanity.com/paper/2203.09505/) (2022)
- [What do navigation agents learn about their environment?](https://mlsanity.com/paper/2206.08500/) (2022)
- [The SVD of Convolutional Weights: A CNN Interpretability Framework](https://mlsanity.com/paper/2208.06894/) (2022)
- [Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts](https://mlsanity.com/paper/2206.10611/) (2022)
- [Feature Accentuation: Revealing 'What' Features Respond to in Natural Images](https://mlsanity.com/paper/2402.10039/) (2024)
- [Sparse Oblique Decision Trees: A Tool to Understand and Manipulate Neural Net Features](https://mlsanity.com/paper/2104.02922/) (2021)
- [DeepVerge: Classification of Roadside Verge Biodiversity and Conservation Potential](https://mlsanity.com/paper/2206.04271/) (2022)
- [Towards glass-box CNNs](https://mlsanity.com/paper/2101.10443/) (2021)
- [Assessing learned features of Deep Learning applied to EEG](https://mlsanity.com/paper/2111.04309/) (2021)
- [Flow AM: Generating Point Cloud Global Explanations by Latent Alignment](https://mlsanity.com/paper/2404.18760/) (2024)
- [Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation](https://mlsanity.com/paper/2208.03217/) (2022)
- [FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks](https://mlsanity.com/paper/2305.10121/) (2023)
- [Targeted Background Removal Creates Interpretable Feature Visualizations](https://mlsanity.com/paper/2306.13178/) (2023)
- [Explaining Deep Face Algorithms through Visualization: A Survey](https://mlsanity.com/paper/2309.14715/) (2023)
- [Understanding Inhibition Through Maximally Tense Images](https://mlsanity.com/paper/2406.05598/) (2024)
- [Multi-channel multi-speaker transformer for speech recognition](https://mlsanity.com/paper/2601.02688/) (2026)

## Abstract (arXiv)

Convolutional Neural Network (CNN) has been successful in image recognition tasks, and recent works shed lights on how CNN separates different classes with the learned inter-class knowledge through visualization. In this work, we instead visualize the intra-class knowledge inside CNN to better understand how an object class is represented in the fully-connected layers. To invert the intra-class knowledge into more interpretable images, we propose a non-parametric patch prior upon previous CNN visualization models. With it, we show how different "styles" of templates for an object class are organized by CNN in terms of location and content, and represented in a hierarchical and ensemble way. Moreover, such intra-class knowledge can be used in many interesting applications, e.g. style-based image retrieval and style-based object completion.