Search Results for author: Furao Shen

Found 14 papers, 3 papers with code

RandomMix: 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 is a very practical technique that can be used to improve the generalization ability of neural networks and prevent overfitting.

Data Augmentation

Image Data Augmentation for Deep Learning: A Survey

no code implementations19 Apr 2022 Suorong Yang, Weikang Xiao, Mengcheng 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 +2

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 Tracking

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, 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

1 code implementation2 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.