Search Results for author: Ya-Xin Li

Found 5 papers, 2 papers with code

Yet Meta Learning Can Adapt Fast, It Can Also Break Easily

no code implementations2 Sep 2020 Han Xu, Ya-Xin Li, Xiaorui Liu, Hui Liu, Jiliang Tang

Thus, in this paper, we perform the initial study about adversarial attacks on meta learning under the few-shot classification problem.

Few-Shot Image Classification Meta-Learning

DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses

3 code implementations13 May 2020 Ya-Xin Li, Wei Jin, Han Xu, Jiliang Tang

DeepRobust is a PyTorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field.

Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies

3 code implementations2 Mar 2020 Wei Jin, Ya-Xin Li, Han Xu, Yiqi Wang, Shuiwang Ji, Charu Aggarwal, Jiliang Tang

As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability.

Adversarial Attack

Multi-wavelet residual dense convolutional neural network for image denoising

no code implementations19 Feb 2020 Shuo-Fei Wang, Wen-Kai Yu, Ya-Xin Li

Networks with large receptive field (RF) have shown advanced fitting ability in recent years.

Image Denoising

Automatic marker-free registration of tree point-cloud data based on rotating projection

no code implementations30 Jan 2020 Xiuxian Xu, Pei Wang, Xiaozheng Gan, Ya-Xin Li, Li Zhang, Qing Zhang, Mei Zhou, Yinghui Zhao, Xinwei Li

In coarse registration, point clouds produced by each scan are projected onto a spherical surface to generate a series of two-dimensional (2D) images, which are used to estimate the initial positions of multiple scans.

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