2 citations · 4 across the 6 of their papers we have counts for
6 papers
Stroke Lesion Segmentation using Multi-Stage Cross-Scale Attention
Liang Shang, William A. Sethares, Anusha Adluru +4
Precise characterization of stroke lesions from MRI data has immense value in prognosticating clinical and cognitive outcomes following a stroke. Manual stroke lesion segmentation…
Segmenting Small Stroke Lesions with Novel Labeling Strategies
Liang Shang, Zhengyang Lou, Andrew L. Alexander +4
Deep neural networks have demonstrated exceptional efficacy in stroke lesion segmentation. However, the delineation of small lesions, critical for stroke diagnosis, remains a chall…
Vision Backbone Enhancement via Multi-Stage Cross-Scale Attention
Liang Shang, Yanli Liu, Zhengyang Lou +4
Convolutional neural networks (CNNs) and vision transformers (ViTs) have achieved remarkable success in various vision tasks. However, many architectures do not consider interactio…
SimHaze: game engine simulated data for real-world dehazing
Zhengyang Lou, Huan Xu, Fangzhou Mu +7
Deep models have demonstrated recent success in single-image dehazing. Most prior methods consider fully supervised training and learn from paired clean and hazy images, where a ha…
Improved Input Reprogramming for GAN Conditioning
Tuan Dinh, Daewon Seo, Zhixu Du +2
We study the GAN conditioning problem, whose goal is to convert a pretrained unconditional GAN into a conditional GAN using labeled data. We first identify and analyze three approa…
GenLabel: Mixup Relabeling using Generative Models
Jy-yong Sohn, Liang Shang, Hongxu Chen +3
Mixup is a data augmentation method that generates new data points by mixing a pair of input data. While mixup generally improves the prediction performance, it sometimes degrades…