# Deep Convolutional Neural Networks as Generic Feature Extractors

arXiv: https://arxiv.org/abs/1710.02286 · HTML: https://mlsanity.com/paper/1710.02286/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2017.

## Built on by (most cited first, 10 of 10)

- [Convolutional Neural Networks Do Work with Pre-Defined Filters](https://mlsanity.com/paper/2411.18388/) (2024)
- [Signature-Graph Networks](https://mlsanity.com/paper/2110.11551/) (2021)
- [Learning Spatio-Temporal Specifications for Dynamical Systems](https://mlsanity.com/paper/2112.10714/) (2021)
- [RF Signal Transformation and Classification using Deep Neural Networks](https://mlsanity.com/paper/2204.03564/) (2022)
- [Enhancing Generalization in Convolutional Neural Networks through Regularization with Edge and Line Features](https://mlsanity.com/paper/2410.16897/) (2024)
- [Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors](https://mlsanity.com/paper/2604.12805/) (2026)
- [Pruning Distorted Images in MNIST Handwritten Digits](https://mlsanity.com/paper/2307.14343/) (2023)
- [A comparative analysis of deep learning models for lung segmentation on X-ray images](https://mlsanity.com/paper/2404.06455/) (2024)
- [Mitigating Dimensionality in 2D Rectangle Packing Problem under Reinforcement Learning Schema](https://mlsanity.com/paper/2409.09677/) (2024)
- [Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks](https://mlsanity.com/paper/2410.00129/) (2024)

## Abstract (arXiv)

Recognizing objects in natural images is an intricate problem involving multiple conflicting objectives. Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task. However, the long time needed to train such deep networks is a major drawback. We tackled this problem by reusing a previously trained network. For this purpose, we first trained a deep convolutional network on the ILSVRC2012 dataset. We then maintained the learned convolution kernels and only retrained the classification part on different datasets. Using this approach, we achieved an accuracy of 67.68 % on CIFAR-100, compared to the previous state-of-the-art result of 65.43 %. Furthermore, our findings indicate that convolutional networks are able to learn generic feature extractors that can be used for different tasks.