paper-with-me

Papers

A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classification

2023-11-24 · Xiangyu Xiong, Yue Sun, Xiaohong Liu, Chan-Tong Lam, Tong Tong, Hao Chen, Qinquan Gao, Wei Ke, Tao Tan

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.

📄 PDF Abstract BibTeX arXiv:2311.14388

Code (1)

yXiangXiong/ParaGAN 공식 구현 pytorch

Tasks

Data AugmentationGenerative Adversarial Networkimage-classificationImage ClassificationMedical Image Classification

Similar Papers 제목 키워드 기반

Cyclic Generative Adversarial Networks With Congruent Image-Report Generation For Explainable Medical Image Analysis

2022-11-16 · Dwarikanath Mahapatra

We present a novel framework for explainable labeling and interpretation of medical images. Medical images require specialized professionals for interpretation, and are explained (typically) via elaborate textual reports…

DiagnosticGenerative Adversarial NetworkMedical Image AnalysisMedical Report Generation

Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning

2023-09-04 · Chong Zhang, Mingyu Jin, Qinkai Yu, Haochen Xue 외

Generalized zero-shot learning (GZSL) aims to recognize samples from both seen and unseen classes using only seen class samples for training. However, GZSL methods are prone to bias towards seen classes during inference …

Generalized Zero-Shot LearningMetric LearningZero-Shot Learning

Sliced Wasserstein Generative Models

2017-06-08 · Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li 외

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of hig…

Image GenerationVideo Generation

Sliced Wasserstein Generative Models

2019-04-10 · CVPR 2019 6 · Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li 외

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of hig…

Image GenerationVideo Generation

Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution

2020-09-07 · Rao Muhammad Umer, Christian Micheloni

Recent deep learning based single image super-resolution (SISR) methods mostly train their models in a clean data domain where the low-resolution (LR) and the high-resolution (HR) images come from noise-free settings (sa…

Generative Adversarial NetworkImage Super-ResolutionImage-to-Image TranslationSuper-Resolution+1