Fine-grained zero-sample classification method based on multi-layer semantic supervised attention model

Abstract

The present invention relates to a fine-grained zero-sample classification method based on multi-layer semantic supervised attention model. The local visual features of fine-grained images are extracted by a convolution neural network, and the local visual features of fine-grained images are supervised by the text description information of categories as category semantic features, and the local visual features of fine-grained images are weighted gradually. The loss function of the multi-level semantic supervised attention model is obtained by mapping the class semantic features to the hiddenspace local visual features. The global visual features of fine-grained images are combined with the local visual features weighted by the multi-layer semantic supervised attention model as the new visual features of images. The category semantic features are embedded into the new visual feature space, and the visual features and semantic features of the output of the multi-layer semantic supervised attention network are aligned, and the softmax function is used for classification. The method of the invention can input the extracted visual features and category semantic features, and output the classification result of the image.

Description

technical field [0001] The invention relates to a zero-sample classification method. In particular, it involves a fine-grained zero-shot classification method based on a multi-layer semantically supervised attention model. Background technique [0002] In recent years, the development of deep learning has greatly promoted the great success of computer vision recognition tasks, but most of the current classification models are based on supervised learning models, which not only require a large amount of labeled data, but also require many iterations to train Model parameters. These models have to be retrained when new categories or rare categories without labeled data appear, which severely limits the scalability of traditional classification models. [0003] Humans have the ability to infer new categories with the help of auxiliary information even if they have not seen a certain category of visual samples. For example, a person who has only seen horses but not zebras is ...

AI Technical Summary

Problems solved by technology

These models have to be retrained when new categories or rare categories without labeled data appear, which severely limits the scalability of traditional classification models

Images