# A Methodology for Exploring Deep Convolutional Features in Relation to Hand-Crafted Features with an Application to Music Audio Modeling

arXiv: https://arxiv.org/abs/2106.00110 · HTML: https://mlsanity.com/paper/2106.00110/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 8 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 6 of 6)

- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Deep Scattering Spectrum](https://mlsanity.com/paper/1304.6763/) (2013)
- [Transfer learning for music classification and regression tasks](https://mlsanity.com/paper/1703.09179/) (2017)
- [Joint Time-Frequency Scattering](https://mlsanity.com/paper/1807.08869/) (2018)

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

- [Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap](https://mlsanity.com/paper/2410.07436/) (2024)

## Abstract (arXiv)

Understanding the features learned by deep models is important from a model trust perspective, especially as deep systems are deployed in the real world. Most recent approaches for deep feature understanding or model explanation focus on highlighting input data features that are relevant for classification decisions. In this work, we instead take the perspective of relating deep features to well-studied, hand-crafted features that are meaningful for the application of interest. We propose a methodology and set of systematic experiments for exploring deep features in this setting, where input feature importance approaches for deep feature understanding do not apply. Our experiments focus on understanding which hand-crafted and deep features are useful for the classification task of interest, how robust these features are for related tasks and how similar the deep features are to the meaningful hand-crafted features. Our proposed method is general to many application areas and we demonstrate its utility on orchestral music audio data.