output
20092026
most citedConditional Random Fields as Recurrent Neural Networks

2.4k citations

Showing eess.IVShow all

10 papers · 1 filter

eess.IV2023★ 41 cited

DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution

Yan Wang, Tongtong Su, Yusen Li +3

Recent research on deep convolutional neural networks (CNNs) has provided a significant performance boost on efficient super-resolution (SR) tasks by trading off the performance an…

eess.IV2023★ 19 cited

Multi-Scale U-Shape MLP for Hyperspectral Image Classification

Moule Lin, Weipeng Jing, Donglin Di +2

Hyperspectral images have significant applications in various domains, since they register numerous semantic and spatial information in the spectral band with spatial variability o…

eess.IV2022★ 8 cited

Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN

Yongsong Huang, Qingzhong Wang, Shinichiro Omachi

In this paper, we present a medical AttentIon Denoising Super Resolution Generative Adversarial Network (AID-SRGAN) for diographic image super-resolution. First, we present a medic…

eess.IV2022★ 80 cited

ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images

Huihui Fang, Fei Li, Huazhu Fu +28

Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance, as the vision loss cause…

eess.IV2021★ 13 cited

Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN

Yongsong Huang, Zetao Jiang, Qingzhong Wang +2

Image super-resolution is important in many fields, such as surveillance and remote sensing. However, infrared (IR) images normally have low resolution since the optical equipment…

eess.IV2020★ 1 cited

Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS

Zhihong Pan, Baopu Li, Teng Xi +5

With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image superresolution (SR) methods have achieved impressive performance using deep residual network wi…