Browsing by Author "Zhu, Fangyi"

Now showing 1 - 2 of 2

Image-Text Dual Model for Small-Sample Image Classification
(2017-01-01)
Zhu, Fangyi
;
Li, Xiaoxu
;
Ma, Zhanyu
;
Chen, Guang
;
Peng, Pai
Small-sample classification is a challenging problem in computer vision and has many applications. In this paper, we propose an image-text dual model to improve the classification performance on small-sample dataset. The proposed dual model consists of two submodels, an image classification model and a text classification model. After training the sub-models respectively, we design a novel method to fuse the two sub-models rather than simply combining the two models' results. Our image-text dual model aims to utilize the text information to overcome the problem of training deep models on small-sample datasets. To demonstrate the effectiveness of the proposed dual model, we conduct extensive experiments on LabelMe and UIUC-Sports. Experimental results show that our model is superior to other models. In conclusion, our proposed model can achieve the highest image classification accuracy among all the referred models on LabelMe and UIUC-Sports.
Image-text dual neural network with decision strategy for small-sample image classification
(2019-02-07)
Zhu, Fangyi
;
Ma, Zhanyu
;
Li, Xiaoxu
;
Chen, Guang
;
Chien, Jen-Tzung
Small-sample classification is a challenging problem in computer vision. In this work, we show how to efficiently and effectively utilize semantic information of the annotations to improve the performance of small-sample classification. First, we propose an image-text dual neural network to improve the classification performance on small-sample datasets. The proposed model consists of two sub-models, an image classification model and a text classification model. After training the sub-models separately, we design a novel method to fuse the two sub-models rather than simply combine their results. Our image-text dual neural network aims to utilize the text information to overcome the training problem of deep models on small-sample datasets. Then, we propose to incorporate a decision strategy into the image-text dual neural network to further improve the performance of our original model on few-shot datasets. To demonstrate the effectiveness of the proposed models, we conduct experiments on the LabelMe and UIUC-Sports datasets. Experimental results show that our method is superior to other models. (C) 2018 Elsevier B.V. All rights reserved.