# Leveraging Filter Correlations for Deep Model Compression

arXiv: https://arxiv.org/abs/1811.10559 · HTML: https://mlsanity.com/paper/1811.10559/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 23 of 23)

- [Manifold Regularized Dynamic Network Pruning](https://mlsanity.com/paper/2103.05861/) (2021)
- [Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN](https://mlsanity.com/paper/2107.14444/) (2021)
- [Deep Model Compression based on the Training History](https://mlsanity.com/paper/2102.00160/) (2021)
- [HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels](https://mlsanity.com/paper/2202.10716/) (2022)
- [A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics](https://mlsanity.com/paper/2112.02834/) (2021)
- [WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks](https://mlsanity.com/paper/2302.08185/) (2023)
- [Reducing Redundancy in the Bottleneck Representation of the Autoencoders](https://mlsanity.com/paper/2202.04629/) (2022)
- [Network Pruning via Feature Shift Minimization](https://mlsanity.com/paper/2207.02632/) (2022)
- [WLD-Reg: A Data-dependent Within-layer Diversity Regularizer](https://mlsanity.com/paper/2301.01352/) (2023)
- [Towards Optimal Compression: Joint Pruning and Quantization](https://mlsanity.com/paper/2302.07612/) (2023)
- [Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices](https://mlsanity.com/paper/2108.06128/) (2021)
- [Pushing the Efficiency Limit Using Structured Sparse Convolutions](https://mlsanity.com/paper/2210.12818/) (2022)
- [Optimal Brain Connection: Towards Efficient Structural Pruning](https://mlsanity.com/paper/2508.05521/) (2025)
- [Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data](https://mlsanity.com/paper/2211.02874/) (2022)
- [Edge AI for Internet of Energy: Challenges and Perspectives](https://mlsanity.com/paper/2311.16851/) (2023)
- [Compressing Deep CNNs using Basis Representation and Spectral Fine-tuning](https://mlsanity.com/paper/2105.10436/) (2021)
- [Network Compression via Central Filter](https://mlsanity.com/paper/2112.05493/) (2021)
- [Target Aware Network Architecture Search and Compression for Efficient Knowledge Transfer](https://mlsanity.com/paper/2205.05967/) (2022)
- [On Feature Diversity in Energy-based Models](https://mlsanity.com/paper/2306.01489/) (2023)
- [Compressive Feature Selection for Remote Visual Multi-Task Inference](https://mlsanity.com/paper/2405.09077/) (2024)
- [Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration](https://mlsanity.com/paper/2506.20152/) (2025)
- [TPV: Parameter Perturbations Through the Lens of Test Prediction Variance](https://mlsanity.com/paper/2512.11089/) (2025)
- [Neural Network Pruning via QUBO Optimization](https://mlsanity.com/paper/2604.05856/) (2026)

## Abstract (arXiv)

We present a filter correlation based model compression approach for deep convolutional neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise correlations and drops one of the filters from each such pair. However, instead of discarding one of the filters from each such pair na"ively, the model is re-optimized to make the filters in these pairs maximally correlated, so that discarding one of the filters from the pair results in minimal information loss. Moreover, after discarding the filters in each round, we further finetune the model to recover from the potential small loss incurred by the compression. We evaluate our proposed approach using a comprehensive set of experiments and ablation studies. Our compression method yields state-of-the-art FLOPs compression rates on various benchmarks, such as LeNet-5, VGG-16, and ResNet-50,56, while still achieving excellent predictive performance for tasks such as object detection on benchmark datasets.