Search Results for author: Zailiang Chen

Found 6 papers, 1 papers with code

Improving Knowledge Distillation via Category Structure

1 code implementation ECCV 2020 Zailiang Chen, Xianxian Zheng, Hailan Shen, Ziyang Zeng, Yukun Zhou, Rongchang Zhao

Intra-category structure penalizes the structured relations in samples from the same category and inter-category structure focuses on cross-category relations at a category level.

Knowledge Distillation

Program Classification Using Gated Graph Attention Neural Network for Online Programming Service

no code implementations9 Mar 2019 Mingming Lu, Dingwu Tan, Naixue Xiong, Zailiang Chen, Haifeng Li

The online programing services, such as Github, TopCoder, and EduCoder, have promoted a lot of social interactions among the service users.

General Classification Graph Attention

DDNet: Cartesian-polar Dual-domain Network for the Joint Optic Disc and Cup Segmentation

no code implementations18 Apr 2019 Qing Liu, Xiaopeng Hong, Wei Ke, Zailiang Chen, Beiji Zou

In this paper, we propose a novel segmentation approach, named Cartesian-polar dual-domain network (DDNet), which for the first time considers the complementary of the Cartesian domain and the polar domain.

Feature Importance Segmentation

Dual-attention Focused Module for Weakly Supervised Object Localization

no code implementations11 Sep 2019 Yukun Zhou, Zailiang Chen, Hailan Shen, Qing Liu, Rongchang Zhao, Yixiong Liang

In each branch, the input feature map is deduced into an enhancement map and a mask map, thereby highlighting the most discriminative parts or hiding them.

Object Object Recognition +2

A Refined Equilibrium Generative Adversarial Network for Retinal Vessel Segmentation

no code implementations26 Sep 2019 Yukun Zhou, Zailiang Chen, Hailan Shen, Xianxian Zheng, Rongchang Zhao, Xuanchu Duan

In this work, we present an end-to-end synthetic neural network, containing a symmetric equilibrium generative adversarial network (SEGAN), multi-scale features refine blocks (MSFRB), and attention mechanism (AM) to enhance the performance on vessel segmentation.

Computational Efficiency Generative Adversarial Network +2

EGDCL: An Adaptive Curriculum Learning Framework for Unbiased Glaucoma Diagnosis

no code implementations ECCV 2020 Rongchang Zhao, Xuanlin Chen, Zailiang Chen, Shuo Li

Today's computer-aided diagnosis (CAD) model is still far from the clinical practice of glaucoma detection, mainly due to the training bias originating from 1) the normal-abnormal class imbalance and 2) the rare but significant hard samples in fundus images.

Specificity

Cannot find the paper you are looking for? You can Submit a new open access paper.