A deep learning clustering method for noise images
A technology of deep learning and clustering method, which is applied in the field of deep learning clustering for noisy images, which can solve the problem of modeling clustering effect without noise data, and achieves to improve the clustering effect, increase the distance between classes, and improve the accuracy. Effect
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2019-06-21
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
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 ...
Examples
Embodiment Construction
[0030] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
[0031] Example:
[0032] The present embodiment provides a kind of deep learning clustering method for noise image, described method comprises the following steps:
[0033] Step S1: Construct a deep learning clustering model, the deep learning clustering model includes a convolutional autoencoder network and a second encoder, and the convolutional autoencoder network includes a first encoder and a decoder; using noise-containing The image data is used as the input of the convolutional autoencoder network;
[0034] Step S2: Use an AMsoftmax layer (Additive Margin Softmax, a normalized exponential function that increases the boundary) as the clusterer of the deep learning clustering model, and generate it according to the feature vector generated by the middle coding laye...