Search Results for author: Furao Shen

Found 25 papers, 3 papers with code

NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields

no code implementations29 Nov 2023 Xiaoliang Liu, Furao Shen, Feng Han, Jian Zhao, Changhai Nie

Face recognition (FR) technology plays a crucial role in various applications, but its vulnerability to adversarial attacks poses significant security concerns.

Adversarial Attack Face Recognition

RADAP: A Robust and Adaptive Defense Against Diverse Adversarial Patches on Face Recognition

no code implementations29 Nov 2023 Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie

RADAP employs innovative techniques, such as FCutout and F-patch, which use Fourier space sampling masks to improve the occlusion robustness of the FR model and the performance of the patch segmenter.

Face Recognition

A Simple Geometric-Aware Indoor Positioning Interpolation Algorithm Based on Manifold Learning

no code implementations27 Nov 2023 Suorong Yang, Geng Zhang, Jian Zhao, Furao Shen

Interpolation methodologies have been widely used within the domain of indoor positioning systems.

A Long-Tail Friendly Representation Framework for Artist and Music Similarity

no code implementations8 Sep 2023 Haoran Xiang, Junyu Dai, Xuchen Song, Furao Shen

The investigation of the similarity between artists and music is crucial in music retrieval and recommendation, and addressing the challenge of the long-tail phenomenon is increasingly important.

Metric Learning Music Recommendation +1

GIMM: InfoMin-Max for Automated Graph Contrastive Learning

no code implementations27 May 2023 Xin Xiong, Furao Shen, Xiangyu Wang, Jian Zhao

Many GCL methods with automated data augmentation face the risk of insufficient information as they fail to preserve the essential information necessary for the downstream task.

Contrastive Learning Data Augmentation +2

AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification

no code implementations29 Nov 2022 Suorong Yang, Jinqiao Li, Jian Zhao, Furao Shen

The experimental results on various datasets and CNN models verify that the proposed method outperforms other previous data augmentation methods in image classification tasks.

Adversarial Attack Classification +2

AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance

no code implementations21 Jul 2022 Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie

In this paper, we propose a new data processing and training method, called AugRmixAT, which can simultaneously improve the generalization ability and multiple robustness of neural network models.

Adversarial Robustness

RSTAM: An Effective Black-Box Impersonation Attack on Face Recognition using a Mobile and Compact Printer

no code implementations25 Jun 2022 Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie

Furthermore, we propose a random meta-optimization strategy for ensembling several pre-trained face models to generate more general adversarial masks.

Face Recognition

RandoMix: A mixed sample data augmentation method with multiple mixed modes

no code implementations18 May 2022 Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie

Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains.

Data Augmentation

Image Data Augmentation for Deep Learning: A Survey

no code implementations19 Apr 2022 Suorong Yang, Weikang Xiao, Mengchen Zhang, Suhan Guo, Jian Zhao, Furao Shen

By improving the quantity and diversity of training data, data augmentation has become an inevitable part of deep learning model training with image data.

Data Augmentation Image Classification +3

AutoAdversary: A Pixel Pruning Method for Sparse Adversarial Attack

no code implementations18 Mar 2022 Jinqiao Li, Xiaotao Liu, Jian Zhao, Furao Shen

A special branch of adversarial examples, namely sparse adversarial examples, can fool the target DNNs by perturbing only a few pixels.

Adversarial Attack Network Pruning

Inf-CP: A Reliable Channel Pruning based on Channel Influence

no code implementations5 Dec 2021 Bilan Lai, Haoran Xiang, Furao Shen

We perform extensive experiments to prove that pruning based on the influence function using the idea of ensemble learning will be much more effective than just focusing on error reconstruction.

Ensemble Learning

SASICM A Multi-Task Benchmark For Subtext Recognition

no code implementations13 Jun 2021 Hua Yan, Feng Han, Junyi An, Weikang Xiao, Jian Zhao, Furao Shen

The F1 score of SASICMBERT, whose pretrained model is BERT, is 65. 12%, which is 0. 75% higher than that of SASICMg.

Faster and Simpler Siamese Network for Single Object Tracking

no code implementations7 May 2021 Shaokui Jiang, Baile Xu, Jian Zhao, Furao Shen

With the development of the deep network and the release for a series of large scale datasets for single object tracking, siamese networks have been proposed and perform better than most of the traditional methods.

object-detection Object Detection +1

IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks

no code implementations6 Feb 2021 Junyi An, Fengshan Liu, Jian Zhao, Furao Shen

Inspired by the elastic collision model in physics, we present a general structure which can be integrated into the existing CNNs to improve their performance.

IC Neuron: An Efficient Unit to Construct Neural Networks

no code implementations23 Nov 2020 Junyi An, Fengshan Liu, Jian Zhao, Furao Shen

We believe that the IC neuron can be a basic unit to build network structures.

Temporal Convolutional Attention-based Network For Sequence Modeling

1 code implementation28 Feb 2020 Hongyan Hao, Yan Wang, Siqiao Xue, Yudi Xia, Jian Zhao, Furao Shen

So we propose an exploratory architecture referred to Temporal Convolutional Attention-based Network (TCAN) which combines temporal convolutional network and attention mechanism.

Pairwise Interactive Graph Attention Network for Context-Aware Recommendation

no code implementations18 Nov 2019 Yahui Liu, Furao Shen, Jian Zhao

PIGAT introduces the attention mechanism to consider the importance of each interacted user/item to both the user and the item, which captures user interests, item attractions and their influence on the recommendation context.

Graph Attention Recommendation Systems

Super Interaction Neural Network

1 code implementation29 May 2019 Yang Yao, Xu Zhang, Baile Xu, Furao Shen, Jian Zhao

Recent studies have demonstrated that the convolutional networks heavily rely on the quality and quantity of generated features.

Label Mapping Neural Networks with Response Consolidation for Class Incremental Learning

no code implementations20 May 2019 Xu Zhang, Yang Yao, Baile Xu, Lekun Mao, Furao Shen, Jian Zhao, QIngwei Lin

In this paper, it is the first time to discuss the difficulty without support of old classes in class incremental learning, which is called as softmax suppression problem.

Class Incremental Learning Incremental Learning +1

Operation-aware Neural Networks for User Response Prediction

3 code implementations2 Apr 2019 Yi Yang, Baile Xu, Furao Shen, Jian Zhao

Many deep models are proposed to automatically learn high-order feature interactions.

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