no code implementations • 19 Apr 2024 • Heqi Peng, Yunhong Wang, Ruijie Yang, Beichen Li, Rui Wang, Yuanfang Guo
Specifically, our approach identifies the Principal Adversarial Domains (PADs), i. e., a combination of features of the adversarial examples from different attacks, which possesses large coverage of the entire adversarial feature space.
no code implementations • 19 Apr 2024 • Beichen Li, Yuanfang Guo, Heqi Peng, Yangxi Li, Yunhong Wang
Based on this paradigm, we propose a new perspective to defeat trigger reverse engineering by manipulating the classification confidence of backdoor samples.
no code implementations • 17 Jan 2024 • Junfu Wang, Yuanfang Guo, Liang Yang, Yunhong Wang
Firstly, we show that by applying a GC operation, the separability gains are determined by two factors, i. e., the Euclidean distance of the neighborhood distributions and $\sqrt{\mathbb{E}\left[\operatorname{deg}\right]}$, where $\mathbb{E}\left[\operatorname{deg}\right]$ is the averaged node degree.
no code implementations • 18 Aug 2023 • Hui Miao, Yuanfang Guo, Yunhong Wang
In this paper, we propose the first deep forgery detection approach for fingerprint images, which combines unique ridge features of fingerprint and generation artifacts of the GAN-generated images, to the best of our knowledge.
no code implementations • 1 Jul 2023 • Ruijie Yang, Yuanfang Guo, Junfu Wang, Jiantao Zhou, Yunhong Wang
Specifically, to reduce the model-specific features and obtain better output distributions, we construct a multi-teacher framework, where the knowledge is distilled from different teacher architectures into one student network.
no code implementations • 7 Feb 2023 • Junfu Wang, Yuanfang Guo, Liang Yang, Yunhong Wang
In this paper, we firstly propose a heterophily-aware attention scheme and reveal the benefits of modeling the edge heterophily, i. e., if a GNN assigns different weights to edges according to different heterophilic types, it can learn effective local attention patterns, which enable nodes to acquire appropriate information from distinct neighbors.
1 code implementation • 24 Oct 2022 • Junfu Wang, Yuanfang Guo, Liang Yang, Yunhong Wang
The current success of Graph Neural Networks (GNNs) usually relies on loading the entire attributed graph for processing, which may not be satisfied with limited memory resources, especially when the attributed graph is large.
no code implementations • 23 Sep 2022 • Junfu Wang, Yuanfang Guo, Liang Yang, Yunhong Wang
Extensive experiments demonstrate that our RE-GNN can effectively and efficiently handle the heterogeneous graphs and can be applied to various homogeneous GNNs.
no code implementations • NeurIPS 2021 • Liang Yang, Mengzhe Li, Liyang Liu, bingxin niu, Chuan Wang, Xiaochun Cao, Yuanfang Guo
Based on this attribute homophily rate, we propose a Diverse Message Passing (DMP) framework, which specifies every attribute propagation weight on each edge.
1 code implementation • 16 Aug 2021 • Ruikui Wang, Yuanfang Guo, Ruijie Yang, Yunhong Wang
In this paper, we explore effective mechanisms to boost both of them from the perspective of network hierarchy, where a typical network can be hierarchically divided into output stage, intermediate stage and input stage.
no code implementations • 1 May 2021 • Ruijie Yang, Yunhong Wang, Ruikui Wang, Yuanfang Guo
This portion of distortions, which is induced by unnecessary modifications and lack of proper perceptual distortion constraint, is the target of the proposed framework.
1 code implementation • CVPR 2021 • Junfu Wang, Yunhong Wang, Zhen Yang, Liang Yang, Yuanfang Guo
Graph Neural Networks (GNNs) have achieved tremendous success in graph representation learning.
no code implementations • 5 Mar 2020 • Yong Bai, Yuanfang Guo, Jinjie Wei, Lin Lu, Rui Wang, Yunhong Wang
With the development of deep neural networks, digital fake paintings can be generated by various style transfer algorithms. To detect the fake generated paintings, we analyze the fake generated and real paintings in Fourier frequency domain and observe statistical differences and artifacts.
no code implementations • 26 Nov 2019 • Mingda Wu, Di Huang, Yuanfang Guo, Yunhong Wang
Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but not well handled.
no code implementations • 9 Jan 2018 • Yuanfang Guo, Xiaochun Cao, Wei zhang, Rui Wang
Based on our observations, i. e., potential traces in the hue, saturation, dark and bright channels, we propose two simple yet effective detection methods for fake colorized images: Histogram based Fake Colorized Image Detection (FCID-HIST) and Feature Encoding based Fake Colorized Image Detection (FCID-FE).
Multimedia
no code implementations • CVPR 2017 • Wei Zhang, Xiaochun Cao, Rui Wang, Yuanfang Guo, Zhineng Chen
Second, we further extend bMS to a more general form, namely contrastive binary mean shift (cbMS), which maximizes the contrastive density in binary space, for finding informative patterns that are both frequent and discriminative for the dataset.
no code implementations • CVPR 2017 • Yanyang Yan, Wenqi Ren, Yuanfang Guo, Rui Wang, Xiaochun Cao
The proposed method takes advantage of both Bright and Dark Channel Prior.