Method and device for training and using target detection model

The invention discloses a method and a device for training and using a target detection model. The training method comprises: inputting an image into a feature extraction network of the target detection model to obtain a feature map of the image, the image comprising a plurality of target objects, the plurality of target objects each comprising a plurality of detection parts, the plurality of detection parts comprising a first detection part and a second detection part; the feature map is input into an affiliation detection network of the target detection model to obtain a first result and a second result, the first result comprises detection data representing the first detection part, and the second result comprises detection data representing a second detection part belonging to the same target object as the first detection part; and updating the target detection model according to the loss of the first result and the loss of the second result. 本公开披露了一种训练和使用目标检测模型的方法和装置。所述训练方法包括：将图像输入所述目标检测模型的特征提取网络，以获取所述图像