# An advanced YOLOv3 method for small object detection

arXiv: https://arxiv.org/abs/2212.02809 · HTML: https://mlsanity.com/paper/2212.02809/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [CSPNet: A New Backbone that can Enhance Learning Capability of CNN](https://mlsanity.com/paper/1911.11929/) (2019)
- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Mish: A Self Regularized Non-Monotonic Activation Function](https://mlsanity.com/paper/1908.08681/) (2019)
- [Single-Shot Refinement Neural Network for Object Detection](https://mlsanity.com/paper/1711.06897/) (2017)
- [Perceptual Generative Adversarial Networks for Small Object Detection](https://mlsanity.com/paper/1706.05274/) (2017)
- [Augmentation for small object detection](https://mlsanity.com/paper/1902.07296/) (2019)
- [Scale Match for Tiny Person Detection](https://mlsanity.com/paper/1912.10664/) (2019)
- [BlitzNet: A Real-Time Deep Network for Scene Understanding](https://mlsanity.com/paper/1708.02813/) (2017)
- [Extended Feature Pyramid Network for Small Object Detection](https://mlsanity.com/paper/2003.07021/) (2020)
- [HRDNet: High-resolution Detection Network for Small Objects](https://mlsanity.com/paper/2006.07607/) (2020)
- [Small Object Detection using Context and Attention](https://mlsanity.com/paper/1912.06319/) (2019)
- [Intrinsic Relationship Reasoning for Small Object Detection](https://mlsanity.com/paper/2009.00833/) (2020)
- [Real Time Multi-Class Object Detection and Recognition Using Vision Augmentation Algorithm](https://mlsanity.com/paper/2003.07442/) (2020)

## 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.