基于注意力机制和图卷积的小样本分类网络

doi:10.3778/j.issn.1002-8331.2104-0275

摘要/Abstract

摘要：

Deep neural networks have dominated image recognition task with large amounts of labeled data. But training a well-performing network on a smaller dataset is still a very challenging task. How to learn from limited labeled data is a key research with excellent scenarios and potential applications. There are many ways to solve few-shot recognition problem, but there is still a problem of low recognition accuracy. The fundamental reason is that in few-shot learning, the traditional neural network can only accept a small amount of labeled data, which makes the network unable to obtain enough information for identification. Therefore, the paper proposes a few-shot classification model based on attention mechanism and graph convolutional neural network, which can not only extract features better, but also make full use of the features to classify the target image. Through the attention mechanism, it can guide the neural network to pay attention to more useful information, and graph convolution enables the network to make more accurate judgments by using the information from other classes of support set. Through many experiments, it is proved that the classification accuracy of the model on the Omniglot dataset and the miniImageNet dataset surpasses the original relational network which based on traditional neural network.

关键词: few-shot learning, image recognition, attention mechanism, graph convolutional network

Abstract:

Key words: few-shot learning, image recognition, attention mechanism, graph convolutional network

王晓茹，张珩. 基于注意力机制和图卷积的小样本分类网络[J]. 计算机工程与应用, 2021, 57(19): 164-170.

WANG Xiaoru, ZHANG Heng. Relation Network Based on Attention Mechanism and Graph Convolution for Few-Shot Learning[J]. Computer Engineering and Applications, 2021, 57(19): 164-170.

参考文献

[1] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv：1409. 1556，2014.
[2] SZEGEDY C，LIU W，JIA Y，et al.Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition，2015.
[3] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognitions[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition，2016.
[4] HUANG G，LIU Z，LAURENS V D M，et al.Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017.
[5] FINK M.Object classification from a single example utilizing class relevance metrics[C]//Advances in Neural Information Processing Systems 17，December 13-18，2004.
[6] FEIFEI L，FERGUS R，PERONA P.One-shot learning of object categories[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2006，28（4）：594-611.
[7] THRUN S.Lifelong learning algorithms[M]//Learning to learn.[S.l.]：Kluwer Academic Publishers，1998.
[8] KOCH G，ZEMEL R，SALAKHUTDINOV R.Siamese neural networks for one-shot image recognition[D].Toronto，Ontario，Canada：University of Toronto，2015.
[9] VINYALS O，BLUNDELL C，LILLICRAP T，et al.Matching networks for one shot learning[C]//Advances in Neural Information Processing Systems，2016：3630-3638.
[10] GARCIA V，BRUNA J.Few-shot learning with graph neural networks[J].arXiv：1711.04043，2017.
[11] SNELL J，SWERSKY K，ZEMEL R S.Prototypical networks for fewshot learning[J].arXiv：1703.05175，2017.
[12] SUNG F，YANG Y，ZHANG L，et al.Learning to compare：Relation network for few-shot learning[J].arXiv：1711.06025，2017.
[13] WU Z，LI Y，GUO L，et al.PARN：Position-aware relation networks for few-shot learning[C]//2019 IEEE/CVF International Conference on Computer Vision，2019.
[14] WU F，SMITH J S，LU W，et al.Attentive prototype few-shot learning with capsule network-based embedding[C]//2020 European Conference on Computer Vision，2020.
[15] HARIHARAN B，GIRSHICK R.Low-shot visual recognition by shrinking and hallucinating features[C]//2017 IEEE International Conference on Computer Vision，2017.
[16] WANG Y，GIRSHICK R，HEBERT M，et al.Low-shot learning from imaginary data[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018.
[17] ANTONIOU A，STORKEY A，EDWARDS H.Data augmentation generative adversarial networks[J].arXiv：1711. 04340，2017.
[18] FINN C，ABBEEL P，LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proceedings of the 34th International Conference on Machine Learning，2017.
[19] RUSU A A，RAO D，SYGNOWSKI J，et al.Meta-learning with latent embedding optimization[J].arXiv：1807.05960，2018.
[20] ZHOU L，CUI P，YANG S，et al.Learning to learn image classifiers with visual analogy[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020.
[21] FLENNERHAG S，RUSU A A，PASCANU R，et al.Meta-learning with warped gradient descent[J].arXiv：1909. 00025，2019.
[22] BAHDANAU D，CHO K，BENGIO Y.Neural machine translation by jointly learning to align and translate[J].arXiv：1409.0473，2014.
[23] XU K，BA J，KIROS R，CHO K，et al.Show，Attend and Tell：Neural image caption generation with visual attention[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning，2015.
[24] WU Z，PAN S，CHEN F，et al.A comprehensive survey on graph neural networks[J].IEEE Transactions on Neural Networks and Learning Systems，2020，32（1）：4-24.
[25] DEFFERRARD M，BRESSON X，VANDERGHEYNST P.Convolutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Processing Systems，2016.
[26] KIPF T N，WELLING M.Semi-supervised classification with graph convolutional networks[J].arXiv：1609.02907，2016.
[27] WANG X，GIRSHICK R，GUPTA A，et al.Non-local neural networks[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：7794-7803.
[28] WOO S，PARK J，LEE J Y，et al.CBAM：Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision，2018.