# Feature Representation in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1507.02313 · HTML: https://mlsanity.com/paper/1507.02313/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2015.

## Built on by (most cited first, 7 of 7)

- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Prediction](https://mlsanity.com/paper/2104.09713/) (2021)
- [Deep Features for training Support Vector Machine](https://mlsanity.com/paper/2104.03488/) (2021)
- [Deep Learning and Computer Vision Techniques for Microcirculation Analysis: A Review](https://mlsanity.com/paper/2205.05493/) (2022)
- [Collaborative Prediction: To Join or To Disjoin Datasets](https://mlsanity.com/paper/2506.11271/) (2025)
- [Towards Predicting the Success of Transfer-based Attacks by Quantifying Shared Feature Representations](https://mlsanity.com/paper/2412.05351/) (2024)
- [Explaining Model Overfitting in CNNs via GMM Clustering](https://mlsanity.com/paper/2412.10457/) (2024)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) are powerful models that achieve impressive results for image classification. In addition, pre-trained CNNs are also useful for other computer vision tasks as generic feature extractors. This paper aims to gain insight into the feature aspect of CNN and demonstrate other uses of CNN features. Our results show that CNN feature maps can be used with Random Forests and SVM to yield classification results that outperforms the original CNN. A CNN that is less than optimal (e.g. not fully trained or overfitting) can also extract features for Random Forest/SVM that yield competitive classification accuracy. In contrast to the literature which uses the top-layer activations as feature representation of images for other tasks, using lower-layer features can yield better results for classification.