PDNet by Partial Deep Convolution: A Better Lightweight Detector
Open Access
- 2 February 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (3) , 591
Abstract
Model lightweighting is significant in edge computing and mobile devices. Current studies on fast network design mainly focuses on model computation compression and speedup. Many models aim to compress models by dealing with redundant feature maps. However, most of these methods choose to preserve the feature maps with simple manipulations and do not effectively reduce redundant feature maps. This paper proposes a new convolution module, PDConv, which compresses redundant feature maps to reduce network complexity and increase network width to maintain accuracy. PDConv (Partial Deep Convolution) outperforms traditional methods in handling redundant feature maps, particularly in deep networks. Its FLOPs are comparable to deep separable convolution but with higher accuracy. This paper proposes PDBottleNeck and PDC2f (Partial Deep CSPDarknet53 to 2-Stage FPN) and build the lightweight network PDNet for experimental validation using the PASCAL VOC dataset. Compared to the popular HorNet, our method achieves an improvement of more than 25% in FLOPs and 1.8% in mAP50:95 accuracy. On the CoCo2017 dataset, our large PDNet achieves a 0.5% improvement in mAP75 and lower FLOPs than the latest RepVit.Keywords
Funding Information
- Shenyang Young and Middle aged Science and Technology Innovation Talent Support Program—Research and Application of Key Technologies for real-time Industrial Visual Defect Detection (RC220452, 22-316-1-10)
- 2022 Shenyang Science and Technology Plan ‘Jie Bang Gua Shuai’ Key Core Technology Tackling Project (Shenyang Bureau of Science and Technology) (RC220452, 22-316-1-10)
This publication has 32 references indexed in Scilit:
- CondenseNet V2: Sparse Feature Reactivation for Deep Networks2021
- Involution: Inverting the Inherence of Convolution for Visual Recognition2021
- FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions2020
- GhostNet: More Features From Cheap Operations2020
- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search2019
- MnasNet: Platform-Aware Neural Architecture Search for Mobile2019
- CondenseNet: An Efficient DenseNet Using Learned Group Convolutions2018
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009