# Layer-Wise Data-Free CNN Compression

arXiv: https://arxiv.org/abs/2011.09058 · HTML: https://mlsanity.com/paper/2011.09058/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization](https://mlsanity.com/paper/2111.09136/) (2021)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Post-training deep neural network pruning via layer-wise calibration](https://mlsanity.com/paper/2104.15023/) (2021)
- [RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging](https://mlsanity.com/paper/2110.01397/) (2021)
- [DeepPCR: Parallelizing Sequential Operations in Neural Networks](https://mlsanity.com/paper/2309.16318/) (2023)
- [SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators](https://mlsanity.com/paper/2410.10714/) (2024)
- [LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time](https://mlsanity.com/paper/2110.04252/) (2021)
- [WebSHAP: Towards Explaining Any Machine Learning Models Anywhere](https://mlsanity.com/paper/2303.09545/) (2023)
- [Sorted Weight Sectioning for Energy-Efficient Unstructured Sparse DNNs on Compute-in-Memory Crossbars](https://mlsanity.com/paper/2410.11298/) (2024)
- [Efficient Reprogramming of Memristive Crossbars for DNNs: Weight Sorting and Bit Stucking](https://mlsanity.com/paper/2410.21730/) (2024)
- [Neural Language Model Pruning for Automatic Speech Recognition](https://mlsanity.com/paper/2310.03424/) (2023)
- [MDM: Manhattan Distance Mapping of DNN Weights for Parasitic-Resistance-Resilient Memristive Crossbars](https://mlsanity.com/paper/2511.04798/) (2025)
- [Security-Enhanced Seed-Based Weight Quantization for Large Language Models](https://mlsanity.com/paper/2609.38477/) (2026)

## Abstract (arXiv)

We present a computationally efficient method for compressing a trained neural network without using real data. We break the problem of data-free network compression into independent layer-wise compressions. We show how to efficiently generate layer-wise training data using only a pretrained network. We use this data to perform independent layer-wise compressions on the pretrained network. We also show how to precondition the network to improve the accuracy of our layer-wise compression method. We present results for layer-wise compression using quantization and pruning. When quantizing, we compress with higher accuracy than related works while using orders of magnitude less compute. When compressing MobileNetV2 and evaluating on ImageNet, our method outperforms existing methods for quantization at all bit-widths, achieving a +0.34% improvement in 8-bit quantization, and a stronger improvement at lower bit-widths (up to a +28.50% improvement at 5 bits). When pruning, we outperform baselines of a similar compute envelope, achieving 1.5 times the sparsity rate at the same accuracy. We also show how to combine our efficient method with high-compute generative methods to improve upon their results.