Open AccessLatent factor model based zero-shot learning
Author(s) -
Y X Q Zhang,
Yinghui Peng,
Jiaqi Li,
C X Zhang,
Dongxiao Yu,
Rui Xia,
Dirk Liu,
Benlong Yang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1914/1/012003
Subject(s) - computer science , feature (linguistics) , artificial intelligence , factor (programming language) , probabilistic latent semantic analysis , key (lock) , benchmark (surveying) , pattern recognition (psychology) , dimension (graph theory) , image (mathematics) , relevance (law) , machine learning , matrix (chemical analysis) , zero (linguistics) , mathematics , philosophy , linguistics , materials science , computer security , geodesy , political science , pure mathematics , law , composite material , programming language , geography
The key of zero-shot learning is to design an appropriate approach to capture the potential relevance between the image visual features and category-level semantic knowledge. There is a lot of data with matrix form in zero-shot recognition problem, such as image label matrix, visual feature matrix and semantic information matrix. Inspired by the latent factor model which tackles recommendation problems well avoid being influenced by sparse matrix, we regard an image as a user and analogize each dimension of the visual feature as an item. The key to our approach is that we model the image recognition as a special recommendation problem by aid of latent factor model. We evaluate our algorithm on three classic benchmark data sets for both conventional and generalized zero-shot setting, the classification results outperform significantly the state-of-art approaches with low calculation cost.