# Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks

arXiv: https://arxiv.org/abs/2403.19969 · HTML: https://mlsanity.com/paper/2403.19969/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 71 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [Movement Pruning: Adaptive Sparsity by Fine-Tuning](https://mlsanity.com/paper/2005.07683/) (2020)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016)
- [Block Pruning For Faster Transformers](https://mlsanity.com/paper/2109.04838/) (2021)
- [Soft Threshold Weight Reparameterization for Learnable Sparsity](https://mlsanity.com/paper/2002.03231/) (2020)
- [Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks](https://mlsanity.com/paper/1909.13144/) (2019)
- [A Review of Sparse Expert Models in Deep Learning](https://mlsanity.com/paper/2209.01667/) (2022)
- [Dynamic Model Pruning with Feedback](https://mlsanity.com/paper/2006.07253/) (2020)
- [MobileOne: An Improved One millisecond Mobile Backbone](https://mlsanity.com/paper/2206.04040/) (2022)
- [Network Quantization with Element-wise Gradient Scaling](https://mlsanity.com/paper/2104.00903/) (2021)
- [Channel Pruning via Automatic Structure Search](https://mlsanity.com/paper/2001.08565/) (2020)
- [Sparse Training via Boosting Pruning Plasticity with Neuroregeneration](https://mlsanity.com/paper/2106.10404/) (2021)

## Built on by (most cited first, 1 of 1)

- [SLA2: Sparse-Linear Attention with Learnable Routing and QAT](https://mlsanity.com/paper/2602.12675/) (2026)

## Abstract (arXiv)

Block pruning, which eliminates contiguous blocks of weights, is a structural pruning method that can significantly enhance the performance of neural processing units (NPUs). In industrial applications, an ideal block pruning algorithm should meet three key requirements: (1) maintain high accuracy across diverse models and tasks, as machine learning deployments on edge devices are typically accuracy-critical; (2) offer precise control over resource constraints to facilitate user adoption; and (3) provide convergence guarantees to prevent performance instability. However, to the best of our knowledge, no existing block pruning algorithm satisfies all three requirements simultaneously. In this paper, we introduce SMART (Separate, Dynamic, and Differentiable) pruning, a novel algorithm designed to address this gap. SMART leverages both weight and activation information to enhance accuracy, employs a differentiable top-k operator for precise control of resource constraints, and offers convergence guarantees under mild conditions. Extensive experiments involving seven models, four datasets, three different block types, and three computer vision tasks demonstrate that SMART pruning achieves state-of-the-art performance in block pruning.