Weak supervision target detection method and system based on transfer learning

Abstract

The invention discloses a weak supervision target detection method and system based on transfer learning; the method comprises the steps: extracting the features of an input strong supervision image and a weak supervision image through a deep convolutional neural network, extracting candidate boxes in the images through a region suggestion network, and obtaining the visual features of different candidate regions; performing feature extraction on category texts in the strong supervision data set and the weak supervision data set, establishing a semantic graph, and performing optimization by using a graph convolutional network to obtain semantic features of all category texts; employing dual-supervised average teacher network structure, which comprises a strong supervised classification and boundary regression student network, a weak supervised multi-instance learning student network and a classification and boundary regression teacher network; and aggregating bounding box information and classification information in the strong supervision data set and the weak supervision data set by using visual features and optimized semantic features, thereby performing bounding box regression and classification on candidate boxes. According to the invention, the weak supervision target detection effect is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a weakly supervised target detection method and system based on transfer learning. Background technique [0002] Object detection is one of the most fundamental tasks in computer vision. In the past few years, many methods based on deep neural networks have achieved great success. However, most methods follow the fully supervised setting, which requires a large number of high-quality annotations, including precise bounding boxes of objects and their corresponding class labels. Such a setup usually takes a lot of time and resources to acquire such annotations. To reduce the labeling cost, Weakly Supervised Object Detection (WSOD) is proposed to train a detection model with only image-level category labels. However, the lack of box-level supervision leads to major problems, such as instance ambiguity and low-quality region proposals. Therefore, there is still a large p...

AI Technical Summary

Problems solved by technology

But this method does not consider the category migration problem, and does not consider the relationship between categories

Images