Search Results for author: Fangyi Zhang

Found 15 papers, 9 papers with code

Learning Fabric Manipulation in the Real World with Human Videos

no code implementations5 Nov 2022 Robert Lee, Jad Abou-Chakra, Fangyi Zhang, Peter Corke

A promising alternative is to learn fabric manipulation directly from watching humans perform the task.

Robust Graph Structure Learning via Multiple Statistical Tests

1 code implementation8 Oct 2022 Yaohua Wang, Fangyi Zhang, Ming Lin, Senzhang Wang, Xiuyu Sun, Rong Jin

A natural way to construct a graph among images is to treat each image as a node and assign pairwise image similarities as weights to corresponding edges.

Face Clustering Graph structure learning

Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

2 code implementations ICLR 2022 Yaohua Wang, Yaobin Zhang, Fangyi Zhang, Ming Lin, Yuqi Zhang, Senzhang Wang, Xiuyu Sun

In Ada-NETS, each face is transformed to a new structure space, obtaining robust features by considering face features of the neighbour images.

Face Clustering

Interpolation variable rate image compression

1 code implementation20 Sep 2021 Zhenhong Sun, Zhiyu Tan, Xiuyu Sun, Fangyi Zhang, Yichen Qian, Dongyang Li, Hao Li

Compression standards have been used to reduce the cost of image storage and transmission for decades.

Image Compression MS-SSIM +1

Fine-Grained AutoAugmentation for Multi-Label Classification

no code implementations12 Jul 2021 Ya Wang, Hesen Chen, Fangyi Zhang, Yaohua Wang, Xiuyu Sun, Ming Lin, Hao Li

Data augmentation is a commonly used approach to improving the generalization of deep learning models.

Classification Data Augmentation +3

A Linkage-based Doubly Imbalanced Graph Learning Framework for Face Clustering

1 code implementation6 Jul 2021 Huafeng Yang, Qijie Shen, Xingjian Chen, Fangyi Zhang, Rong Du

Although imbalance problem has been extensively studied, the impact of imbalanced data on GCN- based linkage prediction task is quite different, which would cause problems in two aspects: imbalanced linkage labels and biased graph representations.

Face Clustering Graph Learning +1

Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection

1 code implementation14 May 2021 Cangning Fan, Fangyi Zhang, Peng Liu, Xiuyu Sun, Hao Li, Ting Xiao, Wei Zhao, Xianglong Tang

In this way, an obvious gap can be produced between the distributions of normal and abnormal data in the target domain, therefore enabling the anomaly detection in the domain.

Anomaly Detection

Spatiotemporal Entropy Model is All You Need for Learned Video Compression

2 code implementations13 Apr 2021 Zhenhong Sun, Zhiyu Tan, Xiuyu Sun, Fangyi Zhang, Dongyang Li, Yichen Qian, Hao Li

The framework of dominant learned video compression methods is usually composed of motion prediction modules as well as motion vector and residual image compression modules, suffering from its complex structure and error propagation problem.

Image Compression motion prediction +3

Tracking the Untrackable

no code implementations17 Jul 2020 Fangyi Zhang

Although short-term fully occlusion happens rare in visual object tracking, most trackers will fail under these circumstances.

Visual Object Tracking

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

9 code implementations CVPR 2019 Bo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan

Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size.

Translation Visual Object Tracking +1

Adversarial Discriminative Sim-to-real Transfer of Visuo-motor Policies

1 code implementation18 Sep 2017 Fangyi Zhang, Jürgen Leitner, ZongYuan Ge, Michael Milford, Peter Corke

Policies can be transferred to real environments with only 93 labelled and 186 unlabelled real images.

Tuning Modular Networks with Weighted Losses for Hand-Eye Coordination

no code implementations15 May 2017 Fangyi Zhang, Jürgen Leitner, Michael Milford, Peter I. Corke

This paper introduces an end-to-end fine-tuning method to improve hand-eye coordination in modular deep visuo-motor policies (modular networks) where each module is trained independently.

Modular Deep Q Networks for Sim-to-real Transfer of Visuo-motor Policies

no code implementations21 Oct 2016 Fangyi Zhang, Jürgen Leitner, Michael Milford, Peter Corke

While deep learning has had significant successes in computer vision thanks to the abundance of visual data, collecting sufficiently large real-world datasets for robot learning can be costly.

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