# A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification

arXiv: https://arxiv.org/abs/2203.15751 · HTML: https://mlsanity.com/paper/2203.15751/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 29 Mar 2022.

## Builds on (most cited first, 15 of 15)

- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation](https://mlsanity.com/paper/1404.0736/) (2014)
- [Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures](https://mlsanity.com/paper/1607.03250/) (2016)
- [Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications](https://mlsanity.com/paper/1511.06530/) (2015)
- [Towards Optimal Structured CNN Pruning via Generative Adversarial Learning](https://mlsanity.com/paper/1903.09291/) (2019)
- [A multi-device dataset for urban acoustic scene classification](https://mlsanity.com/paper/1807.09840/) (2018)
- [Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutions](https://mlsanity.com/paper/2005.14623/) (2020)
- [Acoustic Scene Classification](https://mlsanity.com/paper/1411.3715/) (2014)
- [Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems](https://mlsanity.com/paper/2105.13734/) (2021)
- [SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners](https://mlsanity.com/paper/1806.05320/) (2018)
- [REPrune: Filter Pruning via Representative Election](https://mlsanity.com/paper/2007.06932/) (2020)

## Built on by (most cited first, 11 of 11)

- [Simple Pooling Front-ends For Efficient Audio Classification](https://mlsanity.com/paper/2210.00943/) (2022)
- [Efficient CNNs via Passive Filter Pruning](https://mlsanity.com/paper/2304.02319/) (2023)
- [Continual Learning For On-Device Environmental Sound Classification](https://mlsanity.com/paper/2207.07429/) (2022)
- [Low-complexity CNNs for Acoustic Scene Classification](https://mlsanity.com/paper/2207.11529/) (2022)
- [Efficient Similarity-based Passive Filter Pruning for Compressing CNNs](https://mlsanity.com/paper/2210.17416/) (2022)
- [Compressing audio CNNs with graph centrality based filter pruning](https://mlsanity.com/paper/2305.03391/) (2023)
- [DCASE 2022: Comparative Analysis Of CNNs For Acoustic Scene Classification Under Low-Complexity Considerations](https://mlsanity.com/paper/2206.08007/) (2022)
- [Low-complexity CNNs for Acoustic Scene Classification](https://mlsanity.com/paper/2208.01555/) (2022)
- [Self Similarity Matrix based CNN Filter Pruning](https://mlsanity.com/paper/2211.01814/) (2022)
- [Knowledge Distillation for Efficient Audio-Visual Video Captioning](https://mlsanity.com/paper/2306.09947/) (2023)
- [Improving Acoustic Scene Classification with City Features](https://mlsanity.com/paper/2503.16862/) (2025)

## Abstract (arXiv)

We present a method to develop low-complexity convolutional neural networks (CNNs) for acoustic scene classification (ASC). The large size and high computational complexity of typical CNNs is a bottleneck for their deployment on resource-constrained devices. We propose a passive filter pruning framework, where a few convolutional filters from the CNNs are eliminated to yield compressed CNNs. Our hypothesis is that similar filters produce similar responses and give redundant information allowing such filters to be eliminated from the network. To identify similar filters, a cosine distance based greedy algorithm is proposed. A fine-tuning process is then performed to regain much of the performance lost due to filter elimination. To perform efficient fine-tuning, we analyze how the performance varies as the number of fine-tuning training examples changes. An experimental evaluation of the proposed framework is performed on the publicly available DCASE 2021 Task 1A baseline network trained for ASC. The proposed method is simple, reduces computations per inference by 27%, with 25% fewer parameters, with less than 1% drop in accuracy.