no code implementations • 8 Jan 2024 • Shuxiao Ma, Linyuan Wang, Senbao Hou, Bin Yan
Next, we use the contrast loss function to minimize the distance between the image embedding features and the text embedding features to complete the alignment operation of the stimulus image and text information.
no code implementations • 29 Aug 2023 • Shuxiao Ma, Linyuan Wang, Bin Yan
A convolutional network then maps from this multimodal feature space to voxel space, constructing the multimodal visual information encoding network model.
no code implementations • 1 Aug 2023 • Ruoxi Qin, Linyuan Wang, Xuehui Du, Xingyuan Chen, Bin Yan
The deep neural network has attained significant efficiency in image recognition.
1 code implementation • 3 Jan 2023 • Shuhao Shi, Kai Qiao, Jian Chen, Shuai Yang, Jie Yang, Baojie Song, Linyuan Wang, Bin Yan
However, in addition to low annotation quality, existing benchmarks generally have incomplete user relationships, suppressing graph-based account detection research.
Ranked #1 on Stance Detection on MGTAB
no code implementations • 6 Oct 2022 • Qi Peng, Wenlin Liu, Ruoxi Qin, Libin Hou, Bin Yan, Linyuan Wang
Adversarial attacks are considered the intrinsic vulnerability of CNNs.
no code implementations • 30 Jul 2022 • Qifeng Gao, Rui Ding, Linyuan Wang, Bin Xue, Yuping Duan
The noisy incomplete projection data results in the ill-posedness of the inverse problems.
no code implementations • 8 May 2022 • Shuhao Shi, Jian Chen, Kai Qiao, Shuai Yang, Linyuan Wang, Bin Yan
The Graph Convolutional Networks (GCNs) have achieved excellent results in node classification tasks, but the model's performance at low label rates is still unsatisfactory.
no code implementations • AAAI Workshop AdvML 2022 • Ruoxi Qin, Linyuan Wang, Xuehui Du, Bin Yan, Xingyuan Chen
A new constraints norm is proposed in model training based on these criteria to isolate adversarial transferability without any prior knowledge of adversarial samples.
no code implementations • AAAI Workshop AdvML 2022 • Qi Peng, Ruoxi Qin, Wenlin Liu, Libin Hou, Bin Yan, Linyuan Wang
Recent advances in adversarial attacks uncover the intrinsic vulnerability of modern deep neural networks (DNNs).
no code implementations • 23 Oct 2021 • Ziang Ma, HaiTao Zhang, Linyuan Wang, Jun Yin
Polar pooling plays the role of enriching information collected from the semantic keypoints for stronger classification, while extreme pooling facilitates explicit visual patterns of the object boundary for accurate target state estimation.
no code implementations • 29 Sep 2021 • Shuhao Shi, Pengfei Xie, Xu Luo, Kai Qiao, Linyuan Wang, Jian Chen, Bin Yan
AMC-GNN generates two graph views by data augmentation and compares different layers' output embeddings of Graph Neural Network encoders to obtain feature representations, which could be used for downstream tasks.
no code implementations • 3 Jun 2021 • Pengfei Xie, Linyuan Wang, Ruoxi Qin, Kai Qiao, Shuhao Shi, Guoen Hu, Bin Yan
In this paper, we propose a new gradient iteration framework, which redefines the relationship between the above three.
no code implementations • 6 May 2021 • Ruoxi Qin, Linyuan Wang, Xingyuan Chen, Xuehui Du, Bin Yan
The defense strategies are particularly passive in these processes, and enhancing initiative of such strategies can be an effective way to get out of this arms race.
no code implementations • 8 Aug 2020 • Ziang Ma, Linyuan Wang, HaiTao Zhang, Wei Lu, Jun Yin
While remarkable progress has been made in robust visual tracking, accurate target state estimation still remains a highly challenging problem.
Ranked #13 on Semi-Supervised Video Object Segmentation on VOT2020
no code implementations • 26 Mar 2020 • Kai Qiao, Chi Zhang, Jian Chen, Linyuan Wang, Li Tong, Bin Yan
Except for deep network structure, the task or corresponding big dataset is also important for deep network models, but neglected by previous studies.
no code implementations • 13 Mar 2020 • Kai Qiao, Jian Chen, Linyuan Wang, Chi Zhang, Li Tong, Bin Yan
In this study, we proposed a new GAN-based Bayesian visual reconstruction method (GAN-BVRM) that includes a classifier to decode categories from fMRI data, a pre-trained conditional generator to generate natural images of specified categories, and a set of encoding models and evaluator to evaluate generated images.
no code implementations • 1 Feb 2020 • Zifei Zhang, Kai Qiao, Lingyun Jiang, Linyuan Wang, Bin Yan
To alleviate the tradeoff between the attack success rate and image fidelity, we propose a method named AdvJND, adding visual model coefficients, just noticeable difference coefficients, in the constraint of a distortion function when generating adversarial examples.
1 code implementation • 27 Jul 2019 • Kai Qiao, Chi Zhang, Jian Chen, Linyuan Wang, Li Tong, Bin Yan
Recently, visual encoding based on functional magnetic resonance imaging (fMRI) have realized many achievements with the rapid development of deep network computation.
no code implementations • 12 Apr 2019 • Lingyun Jiang, Kai Qiao, Ruoxi Qin, Linyuan Wang, Jian Chen, Haibing Bu, Bin Yan
In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to them.
no code implementations • 19 Mar 2019 • Kai Qiao, Jian Chen, Linyuan Wang, Chi Zhang, Lei Zeng, Li Tong, Bin Yan
Despite the hierarchically similar representations of deep network and human vision, visual information flows from primary visual cortices to high visual cortices and vice versa based on the bottom-up and top-down manners, respectively.
Neurons and Cognition
no code implementations • 10 Mar 2019 • Ziheng Li, Wenkun Zhang, Linyuan Wang, Ailong Cai, Ningning Liang, Bin Yan, Lei LI
Limited-angle computed tomography (CT) image reconstruction is a challenging reconstruction problem in the fields of CT. With the development of deep learning, the generative adversarial network (GAN) perform well in image restoration by approximating the distribution of training sample data.
Medical Physics
no code implementations • 23 Feb 2019 • Chi Zhang, Kai Qiao, Linyuan Wang, Li Tong, Guoen Hu, Ruyuan Zhang, Bin Yan
In this framework, we employ the transfer learning technique to incorporate a pre-trained DNN (i. e., AlexNet) and train a nonlinear mapping from visual features to brain activity.
no code implementations • 22 Dec 2018 • Chi Zhang, Xiaohan Duan, Linyuan Wang, Yongli Li, Bin Yan, Guoen Hu, Ruyuan Zhang, Li Tong
Furthermore, we show that voxel-encoding models trained on regular images can successfully generalize to the neural responses to AI images but not AN images.
no code implementations • 16 Jan 2018 • Chi Zhang, Kai Qiao, Linyuan Wang, Li Tong, Ying Zeng, Bin Yan
Without semantic prior information, we present a novel method to reconstruct nature images from fMRI signals of human visual cortex based on the computation model of convolutional neural network (CNN).
no code implementations • 2 Jan 2018 • Kai Qiao, Chi Zhang, Linyuan Wang, Bin Yan, Jian Chen, Lei Zeng, Li Tong
We firstly employed the CapsNet to train the nonlinear mapping from image stimuli to high-level capsule features, and from high-level capsule features to image stimuli again in an end-to-end manner.
no code implementations • 29 Jul 2016 • Hanming Zhang, Liang Li, Kai Qiao, Linyuan Wang, Bin Yan, Lei LI, Guoen Hu
The qualitative and quantitative evaluations of experimental results indicate that the proposed method show a stable and prospective performance on artifacts reduction and detail recovery for limited angle tomography.