Class Representation Networks for Few-Shot Learning

In this paper, we proposed a novel network referred as Class Representation Networks (CRNs) to solve the few-shot learning problems. In the proposed CRNs, a high-quality class representation is learned by training a set-based neural network. In addition, a network with fully connected layers was constructed for learning distance metric instead of using a predefined distance metric. Compared with recent methods for few-shot learning, our network achieves state-of-the-art performance for few-shot learning. Extensive experiments on three benchmark datasets validate the effectiveness of our proposed model.

[1]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[2]  Tao Xiang,et al.  Learning to Compare: Relation Network for Few-Shot Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Sergey Levine,et al.  Probabilistic Model-Agnostic Meta-Learning , 2018, NeurIPS.

[4]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[5]  Amos J. Storkey,et al.  Towards a Neural Statistician , 2016, ICLR.

[6]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[7]  Pietro Perona,et al.  Caltech-UCSD Birds 200 , 2010 .

[8]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[9]  Ping Feng,et al.  Learning deep embedding with mini-cluster loss for person re-identification , 2019, Multimedia Tools and Applications.

[10]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[11]  Jongweon Kim,et al.  Art painting detection and identification based on deep learning and image local features , 2018, Multimedia Tools and Applications.

[12]  Seifedine Kadry,et al.  Deep learning convolutional neural network (CNN) With Gaussian mixture model for predicting pancreatic cancer , 2019, Multimedia Tools and Applications.

[13]  Alexandre Lacoste,et al.  TADAM: Task dependent adaptive metric for improved few-shot learning , 2018, NeurIPS.

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[15]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[16]  Joshua B. Tenenbaum,et al.  One shot learning of simple visual concepts , 2011, CogSci.

[17]  Simranjit Singh,et al.  Efficient classification of the hyperspectral images using deep learning , 2018, Multimedia Tools and Applications.

[18]  Stanislav Fort,et al.  Gaussian Prototypical Networks for Few-Shot Learning on Omniglot , 2017, ArXiv.

[19]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Artëm Yankov,et al.  Few-Shot Learning with Metric-Agnostic Conditional Embeddings , 2018, ArXiv.

[21]  Shu Zhan,et al.  Facial micro-expression recognition based on the fusion of deep learning and enhanced optical flow , 2018, Multimedia Tools and Applications.