Small sample image detection method, system, medium and equipment

The invention relates to a small sample image detection method and system, a medium and equipment. The method comprises the following steps: inputting sample data into an image detection model, and performing data enhancement on the sample data to obtain enhanced data; extracting a feature vector from the enhanced data by using a convolutional neural network; generating a first region candidate frame for a classifier to detect and position a target, performing downsampling on the first region candidate frame to obtain a second region candidate frame, and extracting features in the feature vector according to coordinates of the second region candidate frame; performing classification and regression on the incoming features by using a multi-layer full-connection network to obtain the position and the label of a prediction target; and calculating loss of the image detection model and updating parameters of the image detection model. Different from a traditional candidate box-based prediction method, a single can