activity
20182023
most citedConvolutional Neural Networks combined with Runge-Kutta Methods

59 citations · 71 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CV2023★ 2 cited

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

Xu Zheng, Jinjing Zhu, Yexin Liu +3

The ability of scene understanding has sparked active research for panoramic image semantic segmentation. However, the performance is hampered by distortion of the equirectangular…

cs.CV2022★ 8 cited

Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students

Xu Zheng, Yunhao Luo, Chong Fu +2

The popular methods for semi-supervised semantic segmentation mostly adopt a unitary network model using convolutional neural networks (CNNs) and enforce consistency of the model's…

cs.CV2021★ 1 cited

Uncertainty-Aware Deep Co-training for Semi-supervised Medical Image Segmentation

Xu Zheng, Chong Fu, Haoyu Xie +3

Semi-supervised learning has made significant strides in the medical domain since it alleviates the heavy burden of collecting abundant pixel-wise annotated data for semantic segme…

cs.CV2021

A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning

Wenchao Zhang, Chong Fu, Xiangshi Chang +3

Modeling implicit feature interaction patterns is of significant importance to object detection tasks. However, in the two-stage detectors, due to the excessive use of hand-crafted…

cs.CV2020★ 1 cited

Global Context Aware RCNN for Object Detection

Wenchao Zhang, Chong Fu, Haoyu Xie +3

RoIPool/RoIAlign is an indispensable process for the typical two-stage object detection algorithm, it is used to rescale the object proposal cropped from the feature pyramid to gen…

cs.CV2020

Joint Object Contour Points and Semantics for Instance Segmentation

Wenchao Zhang, Chong Fu, Mai Zhu

The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the…

cs.CV2018★ 59 cited

Convolutional Neural Networks combined with Runge-Kutta Methods

Mai Zhu, Bo Chang, Chong Fu

A convolutional neural network can be constructed using numerical methods for solving dynamical systems, since the forward pass of the network can be regarded as a trajectory of a…