A deep learning clustering method for noise images

Abstract

The invention discloses a deep learning clustering method for noise images. The deep learning clustering method comprises the following steps: S1, constructing a deep learning clustering model; S2, adopting an AMsoftmax layer as a clustering device, and generating a clustering result according to the feature vector output by the encoder in the step S1; S3, measuring the similarity between the output of the encoder and the output of the twin network by adopting an L2 norm; S4, adopting KL divergence to measure the distribution difference between the clustering result and the auxiliary target distribution; S5, training a deep learning clustering model; And S6, obtaining a clustering result of the data through the AMsoftmax layer. According to the method, unsupervised clustering can be carried out on image data containing noise, and the problems that most image clustering algorithms do not model noise data and an existing deep clustering algorithm is poor in clustering effect on images with high non-linear characteristics are solved.

Description

technical field [0001] The invention belongs to a clustering method in the field of machine learning, is suitable for clustering processing of noise image data without supervision information, and relates to a noise image-oriented deep learning clustering method. Background technique [0002] In recent years, deep learning has achieved great success in the field of supervised learning tasks, followed by more and more researchers exploring the application of deep learning in the field of unsupervised learning and semi-supervised learning, especially In the two directions of data dimensionality reduction and deep clustering. At present, there are two main types of deep learning clustering algorithms. One is to use deep learning to learn the low-dimensional representation of data, and then perform clustering through traditional clustering algorithms; the other is to use deep learning to combine feature learning with clustering. Classes proceed concurrently. The common method ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies of the above-mentioned prior art. Starting from deep learning and semi-supervised models, a deep learning method oriented to noise data is proposed. The method can perform unsupervised aggregation on image data containing noise. It solves the problem that most image clustering algorithms do not model noise data and the problem that existing deep clustering algorithms have poor clustering effects on images with strong nonlinear features such as faces

Images