Zero sample classification method based on multi-mode dictionary learning

Abstract

The invention provides a zero sample classification method based on multi-mode dictionary learning. The method comprises steps of: establishing a multi-mode dictionary learning model; using the multi-mode dictionary learning model to learn a dictionary matrix D and a compatible matrix V; and by use of the learned dictionary matrix D and the compatible matrix V, achieving zero sample classification. According to the invention, a training sample is used for leaning a dictionary matrix with shared category; the sample is embedded into a hidden space by spanning dictionary atoms; by use of the sample, vectors are embedded into the hidden space; and based on the corresponding relation between a category semantic vector corresponding to the sample and the category, a combined embedding model is learned.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to View More

AI Technical Summary

Benefits of technology

This new technology allows for better understanding about images without being limited or requiring complicated dictionaries that are difficult to interpret correctly. It also includes methods like multidomics where both visual modals (Vs), categorized based on their content) and specific types of objects called classifiers have been combined together. These techniques improve image processing speed while maintaining high accuracy.

Problems solved by technology

This patented technical solution described involves finding representative data points (called labels) about each image without any visible characteristics like coloring or texture. It then uses these labelings to create models called Zebrafish's Zero Shot Classification(ZSC). These models help identify new classes while still being trained correctly. However, they may lack necessary detail when analyzed through vision analysis alone due to their limited representations capabilities. To solve this issue, researches were conducted exploring ways to combine multiple dimensions together to better capture both optical and categoritative aspects simultaneously during training phases.

Images