Variational automatic encoder-based zero-sample image classification method

Abstract

The present invention relates to a zero-sample classification technology in the computer vision field, in particular, a variational automatic encoder-based zero-sample image classification method. Asto the zero-sample image classification method, the distribution of the mappings of semantic features and visual features of categories in a semantic space is fitted, and more efficient semantic associations between the visual features and category semantics are built. According to the variational automatic encoder-based zero-sample image classification method, a variational automatic encoder is adopted to generate embedded semantic features on the basis of the visual features; it is regarded that the variational automatic encoder has a latent variable Z<^>; the latent variable Z<^> is adoptedas an embedded semantic feature; as for a zero-sample image classification task and the visual feature xj of a category-unknown sample, the encoding network of the variational automatic encoder whichis trained on visual categories is utilized to calculate a latent variable Z<^>j which is generated through encoding; the latent variable Z<^>j is adopted as an embedded semantic feature, cosine distances between the latent variable Z<^>j and the semantic feature of each invisible category are calculated, wherein the semantic feature of each invisible category is represented by a symbol describedin the descriptions of the invention; and a category of which the semantic feature is separated from the latent variable Z<^>j by the smallest distance is regarded as the category of the vision sample. The method of the present invention is mainly applied to video classification conditions.

Description

technical field [0001] The invention relates to a zero-sample classification technology oriented to the field of computer vision, in particular to a zero-sample image classification technology based on a variational automatic encoder. Specifically, it involves a zero-shot image classification method based on variational autoencoders. Background technique [0002] With the extensive application of deep learning in the field of image processing, the demand for training data is also expanding. However, obtaining labeled samples requires a lot of manpower. Therefore, the lack of labeled data has become one of the bottlenecks restricting the development of deep learning. The zero-shot problem aims to realize the classification of images that did not participate in the training category through the knowledge transfer of the model. Different from the traditional image classification problem, the zero-shot problem defines the category of image data participating in training as the...

AI Technical Summary

Problems solved by technology

[0002] With the extensive application of deep learning in the field of image processing, the demand for training data is also expanding. However, obtaining labeled samples requires a lot of manpower.

Therefore, the lack of labeled data has become one of the bottlenecks restricting the development of deep learning.

Images