Irrelevant label filtering method based on depth feature clustering and semantic measurement

Abstract

The invention discloses an irrelevant label filtering method based on depth feature clustering and semantic measurement. The method comprises the following steps: 1, acquiring an image set by a sensor; 2, establishing a label set corresponding to the image set; 3, extracting depth features of the images in the image set; 4, clustering the depth features to obtain a cluster; 5, constructing a related semantic label set of the clustering cluster; 6, constructing a to-be-measured label set of the clustering cluster; 7, generating a semantic vector; 8, calculating the relevancy of the semantic vectors; and 9, filtering the irrelevant labels according to the relevancy. According to the method, the clustering cluster is obtained by clustering huge sample image data and used for pre-classifying the sample image data, the clustered sample image data is analyzed, higher effectiveness and correctness are achieved, meanwhile, relevancy measurement is conducted on label semantics, and therefore automatic filtering of irrelevant labels is achieved, and the filtering accuracy is improved, the generalization and robustness of the deep network can be improved.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to an irrelevant label filtering method based on deep feature clustering and semantic measurement. Background technique [0002] With the development of artificial intelligence technology, deep learning technology has been widely used and has become an indispensable part of people's work and life, especially in the fields of computer vision and artificial intelligence. Deep learning technology is a branch of machine learning. It is an algorithm that uses artificial neural networks as the framework to perform representation learning on data. [0003] The convolutional neural network proposed by Yann Lecun et al. has been widely and successfully applied to various image fields such as detection, segmentation, and object recognition. These applications all use large amounts of labeled data. The prerequisite for deep learning technology to achieve good results is to ...

AI Technical Summary

Problems solved by technology

[0005] The current existing technology cannot meet the requirements of filtering irrelevant labels in the data set, so there is an urgent need to filter irrelevant labels in the data set to facilitate subsequent deep learning tasks and improve the generalization and robustness of deep networks. A method for filtering irrelevant labels in datasets

Images