Search Results for author: Zhihua Wang

Found 15 papers, 7 papers with code

Treatment Effect Estimation with Unmeasured Confounders in Data Fusion

no code implementations23 Aug 2022 Anpeng Wu, Kun Kuang, Ruoxuan Xiong, Minqing Zhu, Yuxuan Liu, Bo Li, Furui Liu, Zhihua Wang, Fei Wu

In the presence of unmeasured confounders, we address the problem of treatment effect estimation from data fusion, that is, multiple datasets collected under different treatment assignment mechanisms.

Measuring Perceptual Color Differences of Smartphone Photography

no code implementations26 May 2022 Zhihua Wang, Keshuo Xu, Yang Yang, Jianlei Dong, Shuhang Gu, Lihao Xu, Yuming Fang, Kede Ma

Measuring perceptual color differences (CDs) is of great importance in modern smartphone photography.

Minimizing Memorization in Meta-learning: A Causal Perspective

no code implementations29 Sep 2021 Yinjie Jiang, Zhengyu Chen, Luotian Yuan, Ying WEI, Kun Kuang, Xinhai Ye, Zhihua Wang, Fei Wu

Meta-learning has emerged as a potent paradigm for quick learning of few-shot tasks, by leveraging the meta-knowledge learned from meta-training tasks.

Causal Inference Meta-Learning

Semi-Supervised Deep Ensembles for Blind Image Quality Assessment

1 code implementation26 Jun 2021 Zhihua Wang, Dingquan Li, Kede Ma

Ensemble methods are generally regarded to be better than a single model if the base learners are deemed to be "accurate" and "diverse."

Blind Image Quality Assessment Ensemble Learning

Troubleshooting Blind Image Quality Models in the Wild

no code implementations CVPR 2021 Zhihua Wang, Haotao Wang, Tianlong Chen, Zhangyang Wang, Kede Ma

Recently, the group maximum differentiation competition (gMAD) has been used to improve blind image quality assessment (BIQA) models, with the help of full-reference metrics.

Blind Image Quality Assessment Network Pruning

Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment

no code implementations8 Mar 2020 Zhihua Wang, Kede Ma

We then seek pairs of images by comparing the baseline model with a set of full-reference IQA methods in gMAD.

Active Learning Blind Image Quality Assessment

Learning with Stochastic Guidance for Navigation

1 code implementation27 Nov 2018 Linhai Xie, Yishu Miao, Sen Wang, Phil Blunsom, Zhihua Wang, Changhao Chen, Andrew Markham, Niki Trigoni

Due to the sparse rewards and high degree of environment variation, reinforcement learning approaches such as Deep Deterministic Policy Gradient (DDPG) are plagued by issues of high variance when applied in complex real world environments.

Robotics

Neural Allocentric Intuitive Physics Prediction from Real Videos

no code implementations7 Sep 2018 Zhihua Wang, Stefano Rosa, Yishu Miao, Zihang Lai, Linhai Xie, Andrew Markham, Niki Trigoni

In this framework, real images are first converted to a synthetic domain representation that reduces complexity arising from lighting and texture.

3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations

1 code implementation25 Apr 2018 Zhihua Wang, Stefano Rosa, Bo Yang, Sen Wang, Niki Trigoni, Andrew Markham

This is further confounded by the fact that shape information about encountered objects in the real world is often impaired by occlusions, noise and missing regions e. g. a robot manipulating an object will only be able to observe a partial view of the entire solid.

Defo-Net: Learning Body Deformation using Generative Adversarial Networks

1 code implementation16 Apr 2018 Zhihua Wang, Stefano Rosa, Linhai Xie, Bo Yang, Sen Wang, Niki Trigoni, Andrew Markham

Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots.

Robotics

2D Reconstruction of Small Intestine's Interior Wall

no code implementations15 Mar 2018 Rahman Attar, Xiang Xie, Zhihua Wang, Shigang Yue

The proposed new wireless endoscopic image stitching method consists of two main steps to improve the accuracy and efficiency of image registration.

Image Registration Image Stitching

A Bio-inspired Collision Detecotr for Small Quadcopter

no code implementations14 Jan 2018 Jiannan Zhao, Cheng Hu, Chun Zhang, Zhihua Wang, Shigang Yue

The observed results from the experiments demonstrated that the LGMD collision detector is feasible to work as a vision module for the quadcopter's collision avoidance task.

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