检索结果-内蒙古大学图书馆

ReMarNet: Conjoint relation and margin learning for small-sample image classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xiaoxu Yu, Liyun Yang, Xiaochen Ma, Zhanyu Jing-Hao, Xue Cao, Jie Guo, Jun School of Computer and Communication Lanzhou University of Technology Lanzhou730050 China Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Department of Statistical Science University College London LondonWC1E 6BT United Kingdom

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and-Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype;at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Codes are available at https://***/liyunyu08/ReMarNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Oslnet: Deep small-sample classification with an orthogonal softmax layer

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xiaoxu Chang, Dongliang Ma, Zhanyu Tan, Zheng-Hua Xue, Jing-Hao Cao, Jie Yu, Jingyi Guo, Jun School of Computer and Communication Lanzhou University of Technology China Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Electronic Systems Aalborg University Denmark Department of Statistical Science University College London United Kingdom School of Information Science and Technology ShanghaiTech University China

A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting in small-sample classification, learning more discriminative features from small-sample data is becoming a new trend. To this end, this paper aims to find a subspace of neural networks that can facilitate a large decision margin. Specifically, we propose the Orthogonal Softmax Layer (OSL), which makes the weight vectors in the classification layer remain orthogonal during both the training and test processes. The Rademacher complexity of a network using the OSL is only K1, where K is the number of classes, of that of a network using the fully connected classification layer, leading to a tighter generalization error bound. Experimental results demonstrate that the proposed OSL has better performance than the methods used for comparison on four small-sample benchmark datasets, as well as its applicability to large-sample datasets. Codes are available at: https://***/dongliangchang/OSLNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

SRML: Structure-relation mutual learning network for few-shot image classification

学校读者我要写书评

暂无评论

pattern recognition 2025年 168卷

作者： Li, Xiaoxu Wang, Lang Zhu, Rui Ma, Zhanyu Cao, Jie Xue, Jing-Hao School of Computer and Communication Lanzhou University of Technology Lanzhou730050 China Faculty of Actuarial Science and Insurance Bayes Business School City St George's University of London LondonEC1Y 8TZ United Kingdom Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Lanzhou City University Lanzhou730050 China Department of Statistical Science University College London LondonWC1E 6BT United Kingdom

Few-shot image classification aims at tackling a challenging but practical classification setting, where only few labelled images are available for training. Metric-based methods are main-stream solutions for few-shot image classification, but many of them extract features that are either irrelevant to target objects in the query images or insufficient to describe the local shape or structural patterns within images, which can lead to mis-identification of the target objects, especially when the images are of multiple objects. To resolve this issue, we propose the structure-relation mutual learning (SRML) network, which first learns both the intra-image structural features and the inter-image relational features in a parallel fashion via two parallel branches, the structural feature extractor (SFE) and the relational feature extractor (RFE), and then harnesses mutual learning to enable knowledge exchange between them. In such a manner, the structural features learnt from the SFE branch not only contain the structural patterns within the images, but also focus more on the target objects, guided by the relational knowledge from the RFE branch. In return, the RFE branch can exploit the more-focused structural knowledge to better match the target objects in the support and query images. We conduct extensive experiments on four few-shot classification benchmark datasets to showcase the superior classification of the proposed SRML network, achieving a 3.17% improvement in classification accuracy over the leading competitor, RENet Kang et al. (2021). The code of this work can be found in https://***/Rilliant7/SRML. © 2025 The Authors

关键词： Image correlation

Competing Ratio Loss for Multi-class image Classification

学校读者我要写书评

暂无评论

Competing Ratio Loss for Multi-class image Classification

IEEE Visual Communications and Image Processing Conference

作者： Ke Zhang Xinsheng Wang Yurong Guo Zhenbing Zhao Zhanyu Ma Department of Electronic and Communication Engineering North China Electric Power University Hebei China Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Cross-entropy loss function (CEL) is widely used for training a multi-class classification deep convolutional neural network (DCNN). While CEL has been successfully implemented in image classification tasks, it only focuses on the posterior probability of correct class when the labels of training images are one-hot. It cannot be discriminated against the classes not belong to correct class (wrong classes) directly. Negative Log Likelihood Ratio Loss (NLLR) is proposed to better discriminate the correct class from competing wrong classes. But optimization of the loss function is normally presented as a minimization problem. In training DCNN, the value of NLLR is not constantly positive or negative, which affects the convergence of NLLR adversely. So, we propose competing ratio loss (CRL), which calculates the posterior probability ratio between the correct class and competing wrong classes to better widen the difference between the probability of the correct class and the probabilities of wrong classes, which also assures the value of CRL is constantly positive. Through massive experiments, we demonstrate the effectiveness and robustness of CRL on deep convolutional neural networks, our CRL outperforms CEL and NLLR on CIFAR-10/100 datasets.

关键词：

Omni-supervised Facial Expression recognition via Distilled Data

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Ping Wei, Yunchao Meng, Zibo Deng, Weihong Zhou, Joey Tianyi Yang, Yi Center for Frontier AI Research Agency for Science Technology and Research Singapore Singapore Institute of information science Beijing Jiaotong University Beijing China Centre for Artificial Intelligence University of Technology Sydney Sydney Australia Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China InnoPeak Technology Inc. Palo Alto United States

Facial expression plays an important role in understanding human emotions. Most recently, deep learning based methods have shown promising for facial expression recognition. However, the performance of the current state-of-the-art facial expression recognition (FER) approaches is directly related to the labeled data for training. To solve this issue, prior works employ the pretrain-and-finetune strategy, i.e., utilize a large amount of unlabeled data to pretrain the network and then finetune it by the labeled data. As the labeled data is in a small amount, the final network performance is still restricted. From a different perspective, we propose to perform omni-supervised learning to directly exploit reliable samples in a large amount of unlabeled data for network training. Particularly, a new dataset is firstly constructed using a primitive model trained on a small number of labeled samples to select samples with high confidence scores from a face dataset, i.e., MS-Celeb-1M [1], based on feature-wise similarity. We experimentally verify that the new dataset created in such an omni-supervised manner can significantly improve the generalization ability of the learned FER model. However, as the number of training samples grows, computational cost and training time increase dramatically. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images, significantly improving the training efficiency. We have conducted extensive experiments on widely used benchmarks, where consistent performance gains can be achieved under various settings using the proposed framework. More importantly, the distilled dataset has shown its capabilities of boosting the performance of FER with negligible additional computational costs. We hope this work will serve as a solid baseline and help ease future research in FER. Copyright © 2020, The Authors. All rights reserved.

关键词： Face recognition

Point adversarial self mining: A simple method for facial expression recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Ping Lin, Yuewei Meng, Zibo Lu, Lu Deng, Weihong Zhou, Joey Tianyi Yang, Yi Institute of High Performance Computing Agency for Science Technology and Research Singapore Singapore Centre for Artificial Intelligence University of Technology Sydney Sydney Australia Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Brookhaven National Laboratory UptonNY United States InnoPeak Technology Inc. Palo AltoCA United States Key Laboratory of Medical Molecular Virology School of Basic Medical Sciences Fudan University Shanghai China

In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition. Unlike previous works focusing on designing specific architectures or loss functions to solve this problem, PASM boosts the network capability by simulating human learning processes: providing updated learning materials and guidance from more capable teachers. Specifically, to generate new learning materials, PASM leverages a point adversarial attack method and a trained teacher network to locate the most informative position related to the target task, generating harder learning samples to refine the network. The searched position is highly adaptive since it considers both the statistical information of each sample and the teacher network capability. Other than being provided new learning materials, the student network also receives guidance from the teacher network. After the student network finishes training, the student network changes its role and acts as a teacher, generating new learning materials and providing stronger guidance to train a better student network. The adaptive learning materials generation and teacher/student update can be conducted more than one time, improving the network capability iteratively. Extensive experimental results validate the efficacy of our method over the existing state of the arts for facial expression recognition. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

Feature Fusion of Speech Emotion recognition Based on Deep Learning

学校读者我要写书评

暂无评论

Feature Fusion of Speech Emotion Recognition Based on Deep L...

IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC)

作者： Gang Liu Wei He Bicheng Jin Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Speech emotion recognition (SER) is a hot topic in academia. One of the key issues in improving the performance of SER systems is the choice of speech emotion features. In order to establish a robust speech emotion recognition system, it is essential to select the features which can be a perfect representation of speech emotion attributes. Researchers has done a lot of work, proposed a variety of emotional features and made great progress. Although each kind of features were proven to be effective, most of methods are based on a single type. In this paper, we proposed a method of feature fusion based on deep learning, combining spectral-based features and pitch-based hyper-prosodic features. The experiments show that this method improves the performance of speech emotion recognition system.

关键词： Feature extraction Emotion recognition Speech recognition Hidden Markov models Acoustics Data mining

CNN-Based Audio Front End Processing on Speech recognition

学校读者我要写书评

暂无评论

CNN-Based Audio Front End Processing on Speech Recognition

International Conference on Audio, Language and Image Processing, ICALIP

作者： Ruchao Fan Gang Liu Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Recently, Convolutional Neural Networks (CNNs) have become widely used in the field of speech recognition. Their role is to mitigate the spectral shifts caused by differences between the speakers and the environment. However, how to better use CNN for speech recognition has always been a problem worth exploring. This paper study the usage of CNN as the audio front end processing network based on the acoustic model architecture of Long Short-Term Memory and Connectionist Temporal Classification (LSTM-CTC). Firstly, by comparing the different inputs of the model, a Full-Mel Spectrogram feature that accords with the auditory characteristics is proposed. After determining the input features, this paper explores the principles of CNN parameters design and its role in speech recognition through the comparative experiments of different parameters. Finally, when decoding with phoneme-level language model, we achieve a test set error of 16.9% on the TIMIT phoneme recognition benchmark, which is the best known result of using the CTC as loss function.

关键词： Convolution Kernel Hidden Markov models Spectrogram Computer architecture Speech recognition Filter banks

Deep neural network for analysis of DNA methylation data

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yu, Hong Ma, Zhanyu Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Many researches demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer. There is a strong interest in analyzing the DNA methylation data to find how to distinguish different subtypes of the tumor. However, the conventional statistical methods are not suitable for analyzing the highly dimensional DNA methylation data with bounded support. In order to explicitly capture the properties of the data, we design a deep neural network, which composes of several stacked binary restricted Boltzmann machines, to learn the low dimensional deep features of the DNA methylation data. Experiments show these features perform best in breast cancer DNA methylation data cluster analysis, comparing with some state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks