Basic model weak supervision target detection method based on context awareness self-training

• Main Authors: XU GUANGLUAN, YAN ZHIYUAN, YIN WENXIN, WU YOUMING, DU XUANYI, FENG YINGCHAO
• Format: Patent
• Language: Chinese; English
• Published: 02.02.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention provides a basic model weak supervision target detection method and device based on context awareness self-training, and the method comprises the steps: inputting a plurality of input images into a backbone network for image processing, obtaining a feature map of each input image, carrying out the selective search of the plurality of input images, and obtaining a feature map of each input image; obtaining a plurality of suggestion boxes corresponding to each input image; inputting the feature map of each input image and a plurality of suggestion boxes corresponding to each input image into a ROIAlign structure for feature extraction to obtain an internal region feature, a peripheral region feature and an internal region feature of each suggestion box; obtaining a positioning score matrix and a classification score matrix of each input image according to the internal region feature, the peripheral region feature and the internal region feature of each suggestion box; obtaining a target score matr