mlsanityData to 14 Oct 2026

CSL-YOLO: A New Lightweight Object Detection System for Edge Computing

arXiv 2107.04829 ↗First posted 10 Jul 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

The development of lightweight object detectors is essential due to the limited computation resources. To reduce the computation cost, how to generate redundant features plays a significant role. This paper proposes a new lightweight Convolution method Cross-Stage Lightweight (CSL) Module, to generate redundant features from cheap operations. In the intermediate expansion stage, we replaced Pointwise Convolution with Depthwise Convolution to produce candidate features. The proposed CSL-Module can reduce the computation cost significantly. Experiments conducted at MS-COCO show that the proposed CSL-Module can approximate the fitting ability of Convolution-3x3. Finally, we use the module to construct a lightweight detector CSL-YOLO, achieving better detection performance with only 43% FLOPs and 52% parameters than Tiny-YOLOv4.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 25 of its 31 references that are in the map. First posted on arXiv 10 Jul 2021.

Builds on

25 of 31 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  9. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  12. 2018YOLOv3: An Incremental Improvementcited by 2,659
13 more
  1. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  2. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  3. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  4. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  5. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  6. 2017Focal Loss for Dense Object Detectioncited by 752
  7. 2019GhostNet: More Features from Cheap Operationscited by 410
  8. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 382
  9. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  10. 2018Rethinking ImageNet Pre-trainingcited by 377
  11. 2019Mish: A Self Regularized Non-Monotonic Activation Functioncited by 141
  12. 2018Pelee: A Real-Time Object Detection System on Mobile Devicescited by 56
  13. 2018YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computerscited by 34

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 2.

3 papers.

  1. 2024Optimizing Edge Offloading Decisions for Object Detectioncited by 2
  2. 2024High-Speed Detector For Low-Powered Devices In Aerial Graspingcited by 1
  3. 2022Siamese-NAS: Using Trained Samples Efficiently to Find Lightweight Neural Architecture by Prior Knowledgecited by 0