# Improving Deep Learning Sound Events Classifiers using Gram Matrix Feature-wise Correlations

arXiv: https://arxiv.org/abs/2102.11771 · HTML: https://mlsanity.com/paper/2102.11771/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 23 Feb 2021.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification](https://mlsanity.com/paper/1608.04363/) (2016)
- [A multi-device dataset for urban acoustic scene classification](https://mlsanity.com/paper/1807.09840/) (2018)
- [A Deep Neural Network for Audio Classification with a Classifier Attention Mechanism](https://mlsanity.com/paper/2006.09815/) (2020)

## Built on by (most cited first, 2 of 2)

- [Gramian Multimodal Representation Learning and Alignment](https://mlsanity.com/paper/2412.11959/) (2024)
- [Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matrices](https://mlsanity.com/paper/2501.09538/) (2025)

## Abstract (arXiv)

In this paper, we propose a new Sound Event Classification (SEC) method which is inspired in recent works for out-of-distribution detection. In our method, we analyse all the activations of a generic CNN in order to produce feature representations using Gram Matrices. The similarity metrics are evaluated considering all possible classes, and the final prediction is defined as the class that minimizes the deviation with respect to the features seeing during training. The proposed approach can be applied to any CNN and our experimental evaluation of four different architectures on two datasets demonstrated that our method consistently improves the baseline models.