mlsanityData to 7 Oct 2026

Slim-neck by GSConv: A lightweight-design for real-time detector architectures

arXiv 2206.02424 ↗First posted 6 Jun 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Real-time object detection is significant for industrial and research fields. On edge devices, a giant model is difficult to achieve the real-time detecting requirement and a lightweight model built from a large number of the depth-wise separable convolutional could not achieve the sufficient accuracy. We introduce a new lightweight convolutional technique, GSConv, to lighten the model but maintain the accuracy. The GSConv accomplishes an excellent trade-off between the accuracy and speed. Furthermore, we provide a design suggestion based on the GSConv, Slim-Neck (SNs), to achieve a higher computational cost-effectiveness of the real-time detectors. The effectiveness of the SNs was robustly demonstrated in over twenty sets comparative experiments. In particular, the real-time detectors of ameliorated by the SNs obtain the state-of-the-art (70.9% AP50 for the SODA10M at a speed of ~ 100FPS on a Tesla T4) compared with the baselines. Code is available at https://github.com/alanli1997/slim-neck-by-gsconv

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

38 of 48 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2015Fast R-CNNcited by 2,930
  12. 2018YOLOv3: An Incremental Improvementcited by 2,652
26 more
  1. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  2. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  3. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  4. 2019Searching for MobileNetV3cited by 1,984
  5. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  8. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  9. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  11. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  12. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  13. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  14. 2019GhostNet: More Features from Cheap Operationscited by 410
  15. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  16. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  17. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  18. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  19. 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
  20. 2019Feature Selective Anchor-Free Module for Single-Shot Object Detectioncited by 139
  21. 2017DSSD : Deconvolutional Single Shot Detectorcited by 130
  22. 2020Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentationcited by 98
  23. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  24. 2020PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruningcited by 75
  25. 2021Focal and Efficient IOU Loss for Accurate Bounding Box Regressioncited by 57
  26. 2019WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wildcited by 39

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 6.

7 papers.

  1. 2025Rethinking Features-Fused-Pyramid-Neck for Object Detectioncited by 5
  2. 2025Performance Optimization of YOLO-FEDER FusionNet for Robust Drone Detection in Visually Complex Environmentscited by 2
  3. 2024Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaborationcited by 1
  4. 2025DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detectioncited by 1
  5. 2025ISTD-YOLO: A Multi-Scale Lightweight High-Performance Infrared Small Target Detection Algorithmcited by 0
  6. 2025SBP-YOLO:A Lightweight Real-Time Model for Detecting Speed Bumps and Potholes toward Intelligent Vehicle Suspension Systemscited by 0
  7. 2025A biologically inspired separable learning vision model for real-time traffic object perception in Darkcited by 0