# Compressing Deep CNNs using Basis Representation and Spectral Fine-tuning

arXiv: https://arxiv.org/abs/2105.10436 · HTML: https://mlsanity.com/paper/2105.10436/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 24 references that are in the map.
- First posted on arXiv 21 May 2021.

## Builds on (most cited first, 20 of 20)

- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1808.06866/) (2018)
- [Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation](https://mlsanity.com/paper/1404.0736/) (2014)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [Speeding up Convolutional Neural Networks with Low Rank Expansions](https://mlsanity.com/paper/1405.3866/) (2014)
- [NISP: Pruning Networks using Neuron Importance Score Propagation](https://mlsanity.com/paper/1711.05908/) (2017)
- [Discrimination-aware Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/1810.11809/) (2018)
- [Compressing Neural Networks with the Hashing Trick](https://mlsanity.com/paper/1504.04788/) (2015)
- [Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1909.08174/) (2019)
- [Accelerating Very Deep Convolutional Networks for Classification and Detection](https://mlsanity.com/paper/1505.06798/) (2015)
- [Compression-aware Training of Deep Networks](https://mlsanity.com/paper/1711.02638/) (2017)
- [TRP: Trained Rank Pruning for Efficient Deep Neural Networks](https://mlsanity.com/paper/2004.14566/) (2020)
- [Leveraging Filter Correlations for Deep Model Compression](https://mlsanity.com/paper/1811.10559/) (2018)
- [Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression](https://mlsanity.com/paper/1803.05729/) (2018)
- [Cascaded Projection: End-to-End Network Compression and Acceleration](https://mlsanity.com/paper/1903.04988/) (2019)

## Abstract (arXiv)

We propose an efficient and straightforward method for compressing deep convolutional neural networks (CNNs) that uses basis filters to represent the convolutional layers, and optimizes the performance of the compressed network directly in the basis space. Specifically, any spatial convolution layer of the CNN can be replaced by two successive convolution layers: the first is a set of three-dimensional orthonormal basis filters, followed by a layer of one-dimensional filters that represents the original spatial filters in the basis space. We jointly fine-tune both the basis and the filter representation to directly mitigate any performance loss due to the truncation. Generality of the proposed approach is demonstrated by applying it to several well known deep CNN architectures and data sets for image classification and object detection. We also present the execution time and power usage at different compression levels on the Xavier Jetson AGX processor.