# Audio classification with Dilated Convolution with Learnable Spacings

arXiv: https://arxiv.org/abs/2309.13972 · HTML: https://mlsanity.com/paper/2309.13972/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 26 of 26)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [FractalNet: Ultra-Deep Neural Networks without Residuals](https://mlsanity.com/paper/1605.07648/) (2016)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [Contrastive Audio-Visual Masked Autoencoder](https://mlsanity.com/paper/2210.07839/) (2022)
- [MetaFormer Baselines for Vision](https://mlsanity.com/paper/2210.13452/) (2022)
- [MobileOne: An Improved One millisecond Mobile Backbone](https://mlsanity.com/paper/2206.04040/) (2022)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [Very Deep Convolutional Neural Networks for Raw Waveforms](https://mlsanity.com/paper/1610.00087/) (2016)
- [MAViL: Masked Audio-Video Learners](https://mlsanity.com/paper/2212.08071/) (2022)
- [ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/2106.01621/) (2021)
- [Dilated convolution with learnable spacings](https://mlsanity.com/paper/2112.03740/) (2021)
- [Adapting a ConvNeXt model to audio classification on AudioSet](https://mlsanity.com/paper/2306.00830/) (2023)
- [Sound Event Detection with Depthwise Separable and Dilated Convolutions](https://mlsanity.com/paper/2002.00476/) (2020)
- [Dataset balancing can hurt model performance](https://mlsanity.com/paper/2307.00079/) (2023)
- [E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networks](https://mlsanity.com/paper/2305.18665/) (2023)
- [Dilated Convolution with Learnable Spacings: beyond bilinear interpolation](https://mlsanity.com/paper/2306.00817/) (2023)

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

- [Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM study](https://mlsanity.com/paper/2408.03164/) (2024)

## Abstract (arXiv)

Dilated convolution with learnable spacings (DCLS) is a recent convolution method in which the positions of the kernel elements are learned throughout training by backpropagation. Its interest has recently been demonstrated in computer vision (ImageNet classification and downstream tasks). Here we show that DCLS is also useful for audio tagging using the AudioSet classification benchmark. We took two state-of-the-art convolutional architectures using depthwise separable convolutions (DSC), ConvNeXt and ConvFormer, and a hybrid one using attention in addition, FastViT, and drop-in replaced all the DSC layers by DCLS ones. This significantly improved the mean average precision (mAP) with the three architectures without increasing the number of parameters and with only a low cost on the throughput. The method code is based on PyTorch and is available at https://github.com/K-H-Ismail/DCLS-Audio