2.3k citations · 4.6k across the 84 of their papers we have counts for
10 papers · 2 filters
VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection
Yujun Zhang, Lei Zhu, Wei Feng +5
Lane detection plays a key role in autonomous driving. While car cameras always take streaming videos on the way, current lane detection works mainly focus on individual images (fr…
From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data
Ye Liu, Lei Zhu, Shunda Pei +5
Single image dehazing is a challenging task, for which the domain shift between synthetic training data and real-world testing images usually leads to degradation of existing metho…
Specificity-preserving RGB-D Saliency Detection
Tao Zhou, Deng-Ping Fan, Geng Chen +2
Salient object detection (SOD) on RGB and depth images has attracted more and more research interests, due to its effectiveness and the fact that depth cues can now be conveniently…
Few-Shot Domain Adaptation with Polymorphic Transformers
Shaohua Li, Xiuchao Sui, Jie Fu +7
Deep neural networks (DNNs) trained on one set of medical images often experience severe performance drop on unseen test images, due to various domain discrepancy between the train…
Progressively Normalized Self-Attention Network for Video Polyp Segmentation
Ge-Peng Ji, Yu-Cheng Chou, Deng-Ping Fan +4
Existing video polyp segmentation (VPS) models typically employ convolutional neural networks (CNNs) to extract features. However, due to their limited receptive fields, CNNs can n…
A Multi-Branch Hybrid Transformer Networkfor Corneal Endothelial Cell Segmentation
Yinglin Zhang, Risa Higashita, Huazhu Fu +5
Corneal endothelial cell segmentation plays a vital role inquantifying clinical indicators such as cell density, coefficient of variation,and hexagonality. However, the corneal end…