# DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration

arXiv: https://arxiv.org/abs/1912.10178 · HTML: https://mlsanity.com/paper/1912.10178/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2019.

## Built on by (most cited first, 24 of 24)

- [Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning](https://mlsanity.com/paper/2210.01035/) (2022)
- [MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric](https://mlsanity.com/paper/2403.07839/) (2024)
- [Understanding the Dynamics of DNNs Using Graph Modularity](https://mlsanity.com/paper/2111.12485/) (2021)
- [SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Models](https://mlsanity.com/paper/2410.14720/) (2024)
- [Reassessing Layer Pruning in LLMs: New Insights and Methods](https://mlsanity.com/paper/2411.15558/) (2024)
- [A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models](https://mlsanity.com/paper/2406.07929/) (2024)
- [Layer Folding: Neural Network Depth Reduction using Activation Linearization](https://mlsanity.com/paper/2106.09309/) (2021)
- [SR-init: An interpretable layer pruning method](https://mlsanity.com/paper/2303.07677/) (2023)
- [Practical Network Acceleration with Tiny Sets](https://mlsanity.com/paper/2202.07861/) (2022)
- [Dense Vision Transformer Compression with Few Samples](https://mlsanity.com/paper/2403.18708/) (2024)
- [An Effective Information Theoretic Framework for Channel Pruning](https://mlsanity.com/paper/2408.16772/) (2024)
- [Concurrent Training and Layer Pruning of Deep Neural Networks](https://mlsanity.com/paper/2406.04549/) (2024)
- [MDP: Multidimensional Vision Model Pruning with Latency Constraint](https://mlsanity.com/paper/2504.02168/) (2025)
- [Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint](https://mlsanity.com/paper/2406.12079/) (2024)
- [RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively](https://mlsanity.com/paper/2411.10507/) (2024)
- [FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition](https://mlsanity.com/paper/2505.21571/) (2025)
- [Block Pruning for Enhanced Efficiency in Convolutional Neural Networks](https://mlsanity.com/paper/2312.16904/) (2023)
- [Practical Network Acceleration with Tiny Sets: Hypothesis, Theory, and Algorithm](https://mlsanity.com/paper/2303.00972/) (2023)
- [Complexity-Aware Training of Deep Neural Networks for Optimal Structure Discovery](https://mlsanity.com/paper/2411.09127/) (2024)
- [Online Training and Pruning of Deep Reinforcement Learning Networks](https://mlsanity.com/paper/2507.11975/) (2025)
- [IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning](https://mlsanity.com/paper/2507.14171/) (2025)
- [HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers](https://mlsanity.com/paper/2603.12222/) (2026)
- [EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI](https://mlsanity.com/paper/2607.06982/) (2026)
- [Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning](https://mlsanity.com/paper/2607.11473/) (2026)

## Abstract (arXiv)

Neural network pruning is one of the most popular methods of accelerating the inference of deep convolutional neural networks (CNNs). The dominant pruning methods, filter-level pruning methods, evaluate their performance through the reduction ratio of computations and deem that a higher reduction ratio of computations is equivalent to a higher acceleration ratio in terms of inference time. However, we argue that they are not equivalent if parallel computing is considered. Given that filter-level pruning only prunes filters in layers and computations in a layer usually run in parallel, most computations reduced by filter-level pruning usually run in parallel with the un-reduced ones. Thus, the acceleration ratio of filter-level pruning is limited. To get a higher acceleration ratio, it is better to prune redundant layers because computations of different layers cannot run in parallel. In this paper, we propose our Discrimination based Block-level Pruning method (DBP). Specifically, DBP takes a sequence of consecutive layers (e.g., Conv-BN-ReLu) as a block and removes redundant blocks according to the discrimination of their output features. As a result, DBP achieves a considerable acceleration ratio by reducing the depth of CNNs. Extensive experiments show that DBP has surpassed state-of-the-art filter-level pruning methods in both accuracy and acceleration ratio. Our code will be made available soon.