Target classification and positioning method based on network supervision

Abstract

The invention provides a target classification and positioning method based on network supervision. The target classification and positioning method comprises the following steps: automatically obtaining a large amount of network image data from a search engine according to the category of a to-be-tested target; filtering to remove noise images to form a training sample set; preliminarily constructing a classification and positioning network; and inputting samples in the training sample set into the preliminarily constructed classification and positioning network to perform feature extraction,classifying the features, obtaining position information of the target object, and training the classification and positioning network. According to the end-to-end fine classification and positioningmethod based on network supervision, massive network images easy to obtain are used as a training set, manual annotation is completely removed, only image-level labels are used, an efficient convolutional network is designed, and algorithms such as global average pooling and class activation mapping graphs are fused, so that the performance of the method exceeds that of a weak supervised learningmethod on fine classification tasks and positioning tasks.

Description

Technical field [0001] The present invention relates to the field of computer vision and image processing, and in particular to a method of object classification and positioning based on network supervision that can be used for intelligent automatic identification and other directions. The method can be widely used in the field of automatic identification of mobile phone photographs. Background technique [0002] Target positioning and detection tasks under fully-supervised and weak-supervised learning have developed rapidly in recent years, and the most advanced performance is constantly being refreshed. How to further improve performance? Obviously, designing deeper networks or using more training data are two directions that researchers are exploring. In fact, designing a deeper network is bound to expand data, so how to provide more data to the network is a key issue to be studied. [0003] With a large amount of online visual data, the Internet and social media have become th...

AI Technical Summary

Problems solved by technology

[0007] The above network supervised learning methods have more or less added human intervention or auxiliary labeling, and the performance is still not comparable to weakly supervised learning

Therefore, there are still many problems in the network supervised learning method, and there is a lot of room for improvement.

Images