# Accelerate CNN via Recursive Bayesian Pruning

arXiv: https://arxiv.org/abs/1812.00353 · HTML: https://mlsanity.com/paper/1812.00353/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2018.

## Built on by (most cited first, 27 of 27)

- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [CHIP: CHannel Independence-based Pruning for Compact Neural Networks](https://mlsanity.com/paper/2110.13981/) (2021)
- [Only Train Once: A One-Shot Neural Network Training And Pruning Framework](https://mlsanity.com/paper/2107.07467/) (2021)
- [OTOV2: Automatic, Generic, User-Friendly](https://mlsanity.com/paper/2303.06862/) (2023)
- [Carrying out CNN Channel Pruning in a White Box](https://mlsanity.com/paper/2104.11883/) (2021)
- [Revisiting a kNN-based Image Classification System with High-capacity Storage](https://mlsanity.com/paper/2204.01186/) (2022)
- [Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression](https://mlsanity.com/paper/2502.16638/) (2025)
- [DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data](https://mlsanity.com/paper/2104.11629/) (2021)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [Low-bit Model Quantization for Deep Neural Networks: A Survey](https://mlsanity.com/paper/2505.05530/) (2025)
- [Performance-aware Approximation of Global Channel Pruning for Multitask CNNs](https://mlsanity.com/paper/2303.11923/) (2023)
- [RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets](https://mlsanity.com/paper/2310.10563/) (2023)
- [Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression](https://mlsanity.com/paper/2403.15835/) (2024)
- [LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification](https://mlsanity.com/paper/2204.02965/) (2022)
- [Toward Compact Deep Neural Networks via Energy-Aware Pruning](https://mlsanity.com/paper/2103.10858/) (2021)
- [Survey: Exploiting Data Redundancy for Optimization of Deep Learning](https://mlsanity.com/paper/2208.13363/) (2022)
- [FalconNet: Factorization for the Light-weight ConvNets](https://mlsanity.com/paper/2306.06365/) (2023)
- [OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators](https://mlsanity.com/paper/2312.09411/) (2023)
- [Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy](https://mlsanity.com/paper/2111.09635/) (2021)
- [HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning](https://mlsanity.com/paper/2409.09085/) (2024)
- [Learnable Heterogeneous Convolution: Learning both topology and strength](https://mlsanity.com/paper/2301.05440/) (2023)
- [Filter Pruning For CNN With Enhanced Linear Representation Redundancy](https://mlsanity.com/paper/2310.06344/) (2023)
- [RGP: Neural Network Pruning through Its Regular Graph Structure](https://mlsanity.com/paper/2110.15192/) (2021)
- [Learning k-Level Structured Sparse Neural Networks Using Group Envelope Regularization](https://mlsanity.com/paper/2212.12921/) (2022)
- [Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedure](https://mlsanity.com/paper/2406.03879/) (2024)
- [AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning](https://mlsanity.com/paper/2412.18091/) (2024)
- [Cogradient Descent for Dependable Learning](https://mlsanity.com/paper/2106.10617/) (2021)

## Abstract (arXiv)

Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity. To solve the problem, under the Bayesian framework, we here propose a layer-wise Recursive Bayesian Pruning method (RBP). A new dropout-based measurement of redundancy, which facilitate the computation of posterior assuming inter-layer dependency, is introduced. Specifically, we model the noise across layers as a Markov chain and target its posterior to reflect the inter-layer dependency. Considering the closed form solution for posterior is intractable, we derive a sparsity-inducing Dirac-like prior which regularizes the distribution of the designed noise to automatically approximate the posterior. Compared with the existing methods, no additional overhead is required when the inter-layer dependency assumed. The redundant channels can be simply identified by tiny dropout noise and directly pruned layer by layer. Experiments on popular CNN architectures have shown that the proposed method outperforms several state-of-the-arts. Particularly, we achieve up to bf5.0× and bf2.2× FLOPs reduction with little accuracy loss on the large scale dataset ILSVRC2012 for VGG16 and ResNet50, respectively.