# ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search

arXiv: https://arxiv.org/abs/2110.03858 · HTML: https://mlsanity.com/paper/2110.03858/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 8 Oct 2021.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Designing Neural Network Architectures using Reinforcement Learning](https://mlsanity.com/paper/1611.02167/) (2016)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [State-of-the-art Speech Recognition With Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01769/) (2017)
- [Data-Driven Sparse Structure Selection for Deep Neural Networks](https://mlsanity.com/paper/1707.01213/) (2017)
- [Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers](https://mlsanity.com/paper/1802.00124/) (2018)
- [Channel Pruning via Automatic Structure Search](https://mlsanity.com/paper/2001.08565/) (2020)
- [EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning](https://mlsanity.com/paper/2007.02491/) (2020)
- [DMCP: Differentiable Markov Channel Pruning for Neural Networks](https://mlsanity.com/paper/2005.03354/) (2020)
- [AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates](https://mlsanity.com/paper/1907.03141/) (2019)
- [Heuristic Rank Selection with Progressively Searching Tensor Ring Network](https://mlsanity.com/paper/2009.10580/) (2020)
- [Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1808.07471/) (2018)
- [SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications](https://mlsanity.com/paper/1907.11093/) (2019)
- [ModuleNet: Knowledge-inherited Neural Architecture Search](https://mlsanity.com/paper/2004.05020/) (2020)
- [BiFNet: Bidirectional Fusion Network for Road Segmentation](https://mlsanity.com/paper/2004.08582/) (2020)
- [Conditional Automated Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/2009.09724/) (2020)
- [AACP: Model Compression by Accurate and Automatic Channel Pruning](https://mlsanity.com/paper/2102.00390/) (2021)

## Built on by (most cited first, 4 of 4)

- [BViT: Broad Attention based Vision Transformer](https://mlsanity.com/paper/2202.06268/) (2022)
- [Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search](https://mlsanity.com/paper/2111.07722/) (2021)
- [Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey](https://mlsanity.com/paper/2208.10498/) (2022)
- [Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Tracking](https://mlsanity.com/paper/2603.01706/) (2026)

## Abstract (arXiv)

Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of the traditional rule-based network pruning methods can not reach a sufficient compression ratio with low accuracy loss and are time-consuming as well as laborious. In this paper, we propose Automatic Block-wise and Channel-wise Network Pruning (ABCP) to jointly search the block-wise and channel-wise pruning action with deep reinforcement learning. A joint sample algorithm is proposed to simultaneously generate the pruning choice of each residual block and the channel pruning ratio of each convolutional layer from the discrete and continuous search space respectively. The best pruning action taking both the accuracy and the complexity of the model into account is obtained finally. Compared with the traditional rule-based pruning method, this pipeline saves human labor and achieves a higher compression ratio with lower accuracy loss. Tested on the mobile robot detection dataset, the pruned YOLOv3 model saves 99.5% FLOPs, reduces 99.5% parameters, and achieves 37.3 times speed up with only 2.8% mAP loss. The results of the transfer task on the sim2real detection dataset also show that our pruned model has much better robustness performance.