# Classic versus deep learning approaches to address computer vision challenges

arXiv: https://arxiv.org/abs/2101.09744 · HTML: https://mlsanity.com/paper/2101.09744/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 24 Jan 2021.

## Builds on (most cited first, 17 of 17)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018)
- [Deep Learning vs. Traditional Computer Vision](https://mlsanity.com/paper/1910.13796/) (2019)
- [Deep Multi-Spectral Registration Using Invariant Descriptor Learning](https://mlsanity.com/paper/1801.05171/) (2018)
- [On Detection of Faint Edges in Noisy Images](https://mlsanity.com/paper/1706.07717/) (2017)
- [On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods](https://mlsanity.com/paper/2007.10000/) (2020)
- [Multi-scale Processing of Noisy Images using Edge Preservation Losses](https://mlsanity.com/paper/1803.09420/) (2018)
- [Face Recognition: From Traditional to Deep Learning Methods](https://mlsanity.com/paper/1811.00116/) (2018)
- [Fast Detection of Curved Edges at Low SNR](https://mlsanity.com/paper/1505.06600/) (2015)
- [Registration and Fusion of Multi-Spectral Images Using a Novel Edge Descriptor](https://mlsanity.com/paper/1711.01543/) (2017)
- [Photometric Stereo by Hemispherical Metric Embedding](https://mlsanity.com/paper/1706.08153/) (2017)

## Built on by (most cited first, 1 of 1)

- [Multispectral image fusion based on super pixel segmentation](https://mlsanity.com/paper/2112.11329/) (2021)

## Abstract (arXiv)

Computer vision and image processing address many challenging applications. While the last decade has seen deep neural network architectures revolutionizing those fields, early methods relied on 'classic', i.e., non-learned approaches. In this study, we explore the differences between classic and deep learning (DL) algorithms to gain new insight regarding which is more suitable for a given application. The focus is on two challenging ill-posed problems, namely faint edge detection and multispectral image registration, studying recent state-of-the-art DL and classic solutions. While those DL algorithms outperform classic methods in terms of accuracy and development time, they tend to have higher resource requirements and are unable to perform outside their training space. Moreover, classic algorithms are more transparent, which facilitates their adoption for real-life applications. As both classes of approaches have unique strengths and limitations, the choice of a solution is clearly application dependent.