Saved in:
Bibliographic Details
Main Authors: Xiong, Xiangyu, Sun, Yue, Liu, Xiaohong, Lam, Chan-Tong, Tong, Tong, Chen, Hao, Gao, Qinquan, Ke, Wei, Tan, Tao
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.14388
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912087118184448
author Xiong, Xiangyu
Sun, Yue
Liu, Xiaohong
Lam, Chan-Tong
Tong, Tong
Chen, Hao
Gao, Qinquan
Ke, Wei
Tan, Tao
author_facet Xiong, Xiangyu
Sun, Yue
Liu, Xiaohong
Lam, Chan-Tong
Tong, Tong
Chen, Hao
Gao, Qinquan
Ke, Wei
Tan, Tao
contents Although current data augmentation methods are successful to alleviate the data insufficiency, conventional augmentation are primarily intra-domain while advanced generative adversarial networks (GANs) generate images remaining uncertain, particularly in small-scale datasets. In this paper, we propose a parameterized GAN (ParaGAN) that effectively controls the changes of synthetic samples among domains and highlights the attention regions for downstream classification. Specifically, ParaGAN incorporates projection distance parameters in cyclic projection and projects the source images to the decision boundary to obtain the class-difference maps. Our experiments show that ParaGAN can consistently outperform the existing augmentation methods with explainable classification on two small-scale medical datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2311_14388
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classification
Xiong, Xiangyu
Sun, Yue
Liu, Xiaohong
Lam, Chan-Tong
Tong, Tong
Chen, Hao
Gao, Qinquan
Ke, Wei
Tan, Tao
Computer Vision and Pattern Recognition
Machine Learning
Although current data augmentation methods are successful to alleviate the data insufficiency, conventional augmentation are primarily intra-domain while advanced generative adversarial networks (GANs) generate images remaining uncertain, particularly in small-scale datasets. In this paper, we propose a parameterized GAN (ParaGAN) that effectively controls the changes of synthetic samples among domains and highlights the attention regions for downstream classification. Specifically, ParaGAN incorporates projection distance parameters in cyclic projection and projects the source images to the decision boundary to obtain the class-difference maps. Our experiments show that ParaGAN can consistently outperform the existing augmentation methods with explainable classification on two small-scale medical datasets.
title A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classification
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2311.14388