# Understanding deep features with computer-generated imagery

arXiv: https://arxiv.org/abs/1506.01151 · HTML: https://mlsanity.com/paper/1506.01151/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2015.

## Built on by (most cited first, 13 of 13)

- [Video Summarization Using Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.06072/) (2021)
- [A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks](https://mlsanity.com/paper/2106.02105/) (2021)
- [Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers](https://mlsanity.com/paper/2102.05110/) (2021)
- [PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction](https://mlsanity.com/paper/2404.10620/) (2024)
- [Interactive Analysis of CNN Robustness](https://mlsanity.com/paper/2110.07667/) (2021)
- [HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans](https://mlsanity.com/paper/2309.06107/) (2023)
- [Emergent Riemannian geometry over learning discrete computations on continuous manifolds](https://mlsanity.com/paper/2512.00196/) (2025)
- [Efficient Scopeformer: Towards Scalable and Rich Feature Extraction for Intracranial Hemorrhage Detection](https://mlsanity.com/paper/2302.00220/) (2023)
- [RNNs perform task computations by dynamically warping neural representations](https://mlsanity.com/paper/2512.04310/) (2025)
- [Semantic interpretation for convolutional neural networks: What makes a cat a cat?](https://mlsanity.com/paper/2204.07724/) (2022)
- [Supervised Virtual-to-Real Domain Adaptation for Object Detection Task using YOLO](https://mlsanity.com/paper/2302.13891/) (2023)
- [Feature Chirality in Deep Learning Models](https://mlsanity.com/paper/2305.03966/) (2023)
- [Make it SING: Analyzing Semantic Invariants in Classifiers](https://mlsanity.com/paper/2603.14610/) (2026)

## Abstract (arXiv)

We introduce an approach for analyzing the variation of features generated by convolutional neural networks (CNNs) with respect to scene factors that occur in natural images. Such factors may include object style, 3D viewpoint, color, and scene lighting configuration. Our approach analyzes CNN feature responses corresponding to different scene factors by controlling for them via rendering using a large database of 3D CAD models. The rendered images are presented to a trained CNN and responses for different layers are studied with respect to the input scene factors. We perform a decomposition of the responses based on knowledge of the input scene factors and analyze the resulting components. In particular, we quantify their relative importance in the CNN responses and visualize them using principal component analysis. We show qualitative and quantitative results of our study on three CNNs trained on large image datasets: AlexNet, Places, and Oxford VGG. We observe important differences across the networks and CNN layers for different scene factors and object categories. Finally, we demonstrate that our analysis based on computer-generated imagery translates to the network representation of natural images.