activity
20172026
most citedStructure-measure: A New Way to Evaluate Foreground Maps

109 citations · 144 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

21 papers · 1 filter

cs.CV2026

Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection

Yuhan Gao, Xinqing Li, Xin He +4

Edge detection is a fundamental image analysis task that underpins numerous high-level vision applications. Recent advances in Transformer architectures have significantly improved…

cs.CV2023

Low-Resolution Self-Attention for Semantic Segmentation

Yu-Huan Wu, Shi-Chen Zhang, Yun Liu +6

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision tra…

cs.CV2023

Revisiting Computer-Aided Tuberculosis Diagnosis

Yun Liu, Yu-Huan Wu, Shi-Chen Zhang +3

Tuberculosis (TB) is a major global health threat, causing millions of deaths annually. Although early diagnosis and treatment can greatly improve the chances of survival, it remai…

cs.CV2023

RGB-D Indiscernible Object Counting in Underwater Scenes

Guolei Sun, Xiaogang Cheng, Zhaochong An +5

Recently, indiscernible/camouflaged scene understanding has attracted lots of research attention in the vision community. We further advance the frontier of this field by systemati…

cs.CV2023

PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Clouds

Yun Liu, Xuefeng Yan, Zhilei Chen +3

Self-supervised learning is attracting large attention in point cloud understanding. However, exploring discriminative and transferable features still remains challenging due to th…

cs.CV20214 cited

Boosting Few-shot Semantic Segmentation with Transformers

Guolei Sun, Yun Liu, Jingyun Liang +1

Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentati…