1 code implementation • 24 Aug 2023 • Qiuyu Zhu, Hao Wang, Xuewen Zu, Chengfei Liu
Considering that there are many layers in CNN, through experimental comparison and analysis, MFD Loss acts on multiple front layers of CNN, constrains the output features of each layer and each channel, and performs supervision training jointly with classification loss function during network training.
no code implementations • 10 Apr 2022 • Qiuyu Zhu, Guohui Zheng, Yingying Yan
In this method, there is no need to preprocess the input samples and the computational burden of the algorithm is reduced.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 25 Nov 2021 • Qiuyu Zhu, Xuewen Zu
The loss function only restricts the latent features of the samples, including the norm-adaptive Cosine distance between the latent feature vector of the sample and the center of the predefined evenly-distributed class, and the correlation between the latent features of the samples.
no code implementations • 20 Aug 2021 • Zhengyong Wang, Liquan Shen, Mei Yu, Yufei Lin, Qiuyu Zhu
The proposed framework includes an analysis network and a synthesis network, one for priors exploration and another for priors integration.
no code implementations • NAACL 2021 • Xingwu Sun, Yanling Cui, Hongyin Tang, Qiuyu Zhu, Fuzheng Zhang, Beihong Jin
To tackle this problem, we define a three-level relevance in keyword-document matching task: topic-aware relevance, partially-relevance and irrelevance.
no code implementations • 2 May 2021 • Haiping Hu, Yingying Yan, Qiuyu Zhu, Guohui Zheng
Predefined evenly-distributed class centroids (PEDCC) can be widely used in models and algorithms of pattern classification, such as CNN classifiers, classification autoencoders, clustering, and semi-supervised learning, etc.
no code implementations • 16 Nov 2020 • Joel Q. L. Chang, Qiuyu Zhu, Vincent Y. F. Tan
The multi-armed bandit (MAB) problem is a ubiquitous decision-making problem that exemplifies the exploration-exploitation tradeoff.
2 code implementations • ICML 2020 • Qiuyu Zhu, Vincent Y. F. Tan
The multi-armed bandit (MAB) problem is a classical learning task that exemplifies the exploration-exploitation tradeoff.
no code implementations • 13 Jan 2020 • Qiuyu Zhu, Tiantian Li
Meanwhile, for unlabeled samples, we also use KL divergence to constrain the consistency of the network predictions between unlabeled and augmented samples.
no code implementations • 11 Jun 2019 • Qiuyu Zhu, Zikuang He, Xin Ye
In this paper, we introduce an ensemble method of incremental classifier to alleviate this problem, which is based on the cosine distance between the output feature and the pre-defined center, and can let each task to be preserved in different networks.
3 code implementations • 10 Jun 2019 • Qiuyu Zhu, Zhengyong Wang
The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data augmentation constraint, auto-encoder reconstruction constraint and Sobel smooth constraint to improve the clustering performance.
1 code implementation • 12 Apr 2019 • Qiuyu Zhu, Pengju Zhang, Xin Ye
With the development of convolutional neural networks (CNNs) in recent years, the network structure has become more and more complex and varied, and has achieved very good results in pattern recognition, image classification, object detection and tracking.
no code implementations • 1 Feb 2019 • Qiuyu Zhu, Ruixin Zhang
In this paper, a new autoencoder model - classification supervised autoencoder (CSAE) based on predefined evenly-distributed class centroids (PEDCC) is proposed.
1 code implementation • 7 Mar 2018 • Qiuyu Zhu, Ruixin Zhang
In order to enhance the real-time performance of convolutional neural networks(CNNs), more and more researchers are focusing on improving the efficiency of CNN.