Similarity Distance-Based Label Assignment for Tiny Object Detection

Tiny object detection is becoming one of the most challenging tasks in computer vision because of the limited object size and lack of information. The label assignment strategy is a key factor affecting the accuracy of object detection. Although there are some effective label assignment strategies for tiny objects, most of them focus on reducing the sensitivity to the bounding boxes to increase the number of positive samples and have some fixed hyperparameters need to set. However, more positive samples may not necessarily lead to better detection results, in fact, excessive positive samples may lead to more false positives. In this paper, we introduce a simple but effective strategy named the Similarity Distance (SimD) to evaluate the similarity between bounding boxes. This proposed strategy not only considers both location and shape similarity but also learns hyperparameters adaptively, ensuring that it can adapt to different datasets and various object sizes in a dataset. Our approach can be simply applied in common anchor-based detectors in place of the IoU for label assignment and Non Maximum Suppression (NMS). Extensive experiments on four mainstream tiny object detection datasets demonstrate superior performance of our method, especially, 1. 8 AP points and 4. 1 AP points of very tiny higher than the state-of-the-art competitors on AI-TOD. Code is available at: https://github.com/cszzshi/simd.

Authors

• Shuohao Shi
• Qiang Fang
• Xin Xu
• Tong Zhao

Keywords

• Computer vision
• Sensitivity
• Codes
• Accuracy
• Shape
• Object detection
• Detectors
• Intelligent robots
• Tiny Objects
• Tiny Object Detection
• Hyperparameters
• Positive Samples
• Detection Accuracy
• Similar Shape
• Bounding Box
• Object Size
• Similar Distance
• Maximum Inhibition
• Non-maximum Suppression
• Accurate Object Detection
• Object Detection Dataset
• Training Set
• Negative Samples
• Data Augmentation
• Stochastic Gradient Descent
• Kullback-Leibler
• Normal Parameters
• Small Objects
• Image Object Detection
• Faster R-CNN
• Objects Of Different Sizes
• Negative Threshold
• Positive Threshold
• Small Object Detection
• Two-stage Detectors
• Average Precision