L
Liujuan Cao
Researcher at Xiamen University
Publications - 100
Citations - 2366
Liujuan Cao is an academic researcher from Xiamen University. The author has contributed to research in topics: Computer science & Digital watermarking. The author has an hindex of 19, co-authored 77 publications receiving 1419 citations. Previous affiliations of Liujuan Cao include Columbia University & Harbin Engineering University.
Papers
More filters
Proceedings ArticleDOI
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
Shaohui Lin,Rongrong Ji,Chenqian Yan,Baochang Zhang,Liujuan Cao,Qixiang Ye,Feiyue Huang,David Doermann +7 more
TL;DR: This paper proposes an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner and effectively solves the optimization problem by generative adversarial learning (GAL), which learns a sparse soft mask in a label-free and an end to end manner.
Journal ArticleDOI
A novel features ranking metric with application to scalable visual and bioinformatics data classification
TL;DR: A Max-Relevance-Max-Distance (MRMD) feature ranking method, which balances accuracy and stability of feature ranking and prediction task, and runs faster than other filtering and wrapping methods, such as mRMR and Information Gain.
Proceedings ArticleDOI
Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
TL;DR: A novel Multi-task Collaborative Network (MCN) is proposed to achieve a joint learning of REC and RES for the first time and addresses a key challenge in this multi-task setup, i.e., the prediction conflict.
Proceedings ArticleDOI
Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation
TL;DR: This paper presents an efficient and effective framework termed Weakly Supervised Joint Detection and Segmentation (WS-JDS), which uses their respective failure patterns to complement each other's learning in a multi-task learning scheme for the first time.
Journal ArticleDOI
Vehicle Detection in High-Resolution Aerial Images via Sparse Representation and Superpixels
Ziyi Chen,Cheng Wang,Chenglu Wen,Xiuhua Teng,Yiping Chen,Haiyan Guan,Huan Luo,Liujuan Cao,Jonathan Li +8 more
TL;DR: A superpixel segmentation method designed for aerial images is proposed to control the segmentation with a low breakage rate and obtain a dictionary with high discrimination ability for vehicle detection from high-resolution aerial images.