# Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search

arXiv: https://arxiv.org/abs/2106.14943 · HTML: https://mlsanity.com/paper/2106.14943/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 13 references that are in the map.
- First posted on arXiv 28 Jun 2021.

## Builds on (most cited first, 10 of 10)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Discrimination-aware Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/1810.11809/) (2018)
- [PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning](https://mlsanity.com/paper/2001.00138/) (2020)
- [Bayesian Optimization in AlphaGo](https://mlsanity.com/paper/1812.06855/) (2018)
- [PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices](https://mlsanity.com/paper/1909.05073/) (2019)
- [RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition](https://mlsanity.com/paper/2002.11474/) (2020)

## Built on by (most cited first, 2 of 2)

- [Small Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion](https://mlsanity.com/paper/2401.08017/) (2024)
- [Geometric Perception based Efficient Text Recognition](https://mlsanity.com/paper/2302.03873/) (2023)

## Abstract (arXiv)

Object detection plays an important role in self-driving cars for security development. However, mobile systems on self-driving cars with limited computation resources lead to difficulties for object detection. To facilitate this, we propose a compiler-aware neural pruning search framework to achieve high-speed inference on autonomous vehicles for 2D and 3D object detection. The framework automatically searches the pruning scheme and rate for each layer to find a best-suited pruning for optimizing detection accuracy and speed performance under compiler optimization. Our experiments demonstrate that for the first time, the proposed method achieves (close-to) real-time, 55ms and 99ms inference times for YOLOv4 based 2D object detection and PointPillars based 3D detection, respectively, on an off-the-shelf mobile phone with minor (or no) accuracy loss.