# Visual Saliency-Guided Channel Pruning for Deep Visual Detectors in Autonomous Driving

arXiv: https://arxiv.org/abs/2303.02512 · HTML: https://mlsanity.com/paper/2303.02512/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 4 Mar 2023.

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

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1808.06866/) (2018)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures](https://mlsanity.com/paper/1607.03250/) (2016)
- [Compressing Neural Networks with the Hashing Trick](https://mlsanity.com/paper/1504.04788/) (2015)
- [A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1804.03294/) (2018)
- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [Data-free parameter pruning for Deep Neural Networks](https://mlsanity.com/paper/1507.06149/) (2015)
- [CHIP: CHannel Independence-based Pruning for Compact Neural Networks](https://mlsanity.com/paper/2110.13981/) (2021)
- [Faster CNNs with Direct Sparse Convolutions and Guided Pruning](https://mlsanity.com/paper/1608.01409/) (2016)
- [Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios](https://mlsanity.com/paper/2202.04781/) (2022)
- [Localization-aware Channel Pruning for Object Detection](https://mlsanity.com/paper/1911.02237/) (2019)

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

- [Visual Detector Compression via Location-Aware Discriminant Analysis](https://mlsanity.com/paper/2509.17968/) (2025)
- [Lightweight Temporal Transformer Decomposition for Federated Autonomous Driving](https://mlsanity.com/paper/2506.23523/) (2025)

## Abstract (arXiv)

Deep neural network (DNN) pruning has become a de facto component for deploying on resource-constrained devices since it can reduce memory requirements and computation costs during inference. In particular, channel pruning gained more popularity due to its structured nature and direct savings on general hardware. However, most existing pruning approaches utilize importance measures that are not directly related to the task utility. Moreover, few in the literature focus on visual detection models. To fill these gaps, we propose a novel gradient-based saliency measure for visual detection and use it to guide our channel pruning. Experiments on the KITTI and COCO traffic datasets demonstrate our pruning method's efficacy and superiority over state-of-the-art competing approaches. It can even achieve better performance with fewer parameters than the original model. Our pruning also demonstrates great potential in handling small-scale objects.