mlsanityData to 7 Oct 2026

An advanced YOLOv3 method for small object detection

arXiv 2212.02809 ↗First posted 6 Dec 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Small object detection has important application value in the fields of autonomous driving and drone scene analysis. As one of the most advanced object detection algorithms, YOLOv3 suffers some challenges when detecting small objects, such as the problem of detection failure of small objects and occluded objects. To solve these problems, an improved YOLOv3 algorithm for small object detection is proposed. In the proposed method, the dilated convolutions mish (DCM) module is introduced into the backbone network of YOLOv3 to improve the feature expression ability by fusing the feature maps of different receptive fields. In the neck network of YOLOv3, the convolutional block attention module (CBAM) and multi-level fusion module are introduced to select the important information for small object detection in the shallow network, suppress the uncritical information, and use the fusion module to fuse the feature maps of different scales, so as to improve the detection accuracy of the algorithm. In addition, the Soft-NMS and Complete-IoU (CloU) strategies are applied to candidate frame screening, which improves the accuracy of the algorithm for the detection of occluded objects. The ablation experiment of the MS COCO2017 object detection task proves the effectiveness of several modules introduced in this paper for small object detection. The experimental results on the MS COCO2017, VOC2007, and VOC2012 datasets show that the Average Precision (AP) of this method is 16.5%, 8.71%, and 9.68% higher than that of YOLOv3, respectively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

26 of 41 references.

References · 26

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  4. 2015Fast R-CNNcited by 2,930
  5. 2018YOLOv3: An Incremental Improvementcited by 2,652
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  8. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  9. 2018Path Aggregation Network for Instance Segmentationcited by 796
  10. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  11. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  12. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
14 more
  1. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  2. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 380
  3. 2021Pixel Difference Networks for Efficient Edge Detectioncited by 167
  4. 2019Mish: A Self Regularized Non-Monotonic Activation Functioncited by 141
  5. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  6. 2017Perceptual Generative Adversarial Networks for Small Object Detectioncited by 76
  7. 2019Augmentation for small object detectioncited by 73
  8. 2019Scale Match for Tiny Person Detectioncited by 61
  9. 2017BlitzNet: A Real-Time Deep Network for Scene Understandingcited by 29
  10. 2020Extended Feature Pyramid Network for Small Object Detectioncited by 27
  11. 2020HRDNet: High-resolution Detection Network for Small Objectscited by 25
  12. 2019Small Object Detection using Context and Attentioncited by 21
  13. 2020Intrinsic Relationship Reasoning for Small Object Detectioncited by 3
  14. 2020Real Time Multi-Class Object Detection and Recognition Using Vision Augmentation Algorithmcited by 1

Built on by

Not cited yet.