Proxy Network for Few Shot Learning

The use of a few examples for each class to train a predictive model that can be generalized to novel classes is a crucial and valuable research direction in artificial intelligence. This work addresses this problem by proposing a few-shot learning (FSL) algorithm called proxy network under the architecture of meta-learning. Metric-learning based approaches assume that the data points within the same class should be close, whereas the data points in the different classes should be separated as far as possible in the embedding space. We conclude that the success of metric-learning based approaches lies in the data embedding, the representative of each class, and the distance metric. In this work, we propose a simple but effective end-to-end model that directly learns proxies for class representative and distance metric from data simultaneously. We conduct experiments on CUB and mini-ImageNet datasets in 1-shot-5-way and 5-shot-5-way scenarios, and the experimental results demonstrate the superiority of our proposed method over state-of-the-art methods. Besides, we provide a detailed analysis of our proposed method.

[1]  Lionel M. Ni,et al.  Generalizing from a Few Examples , 2020, ACM Comput. Surv..

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

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

[4]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[5]  Matthew A. Brown,et al.  Low-Shot Learning with Imprinted Weights , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Bharath Hariharan,et al.  Low-Shot Visual Recognition by Shrinking and Hallucinating Features , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[9]  Charu C. Aggarwal,et al.  On the Surprising Behavior of Distance Metrics in High Dimensional Spaces , 2001, ICDT.

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

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

[12]  Raquel Urtasun,et al.  Few-Shot Learning Through an Information Retrieval Lens , 2017, NIPS.

[13]  Martial Hebert,et al.  Low-Shot Learning from Imaginary Data , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[15]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[16]  Pietro Perona,et al.  The Caltech-UCSD Birds-200-2011 Dataset , 2011 .

[17]  Nikos Komodakis,et al.  Dynamic Few-Shot Visual Learning Without Forgetting , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

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

[20]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Yu-Chiang Frank Wang,et al.  A Closer Look at Few-shot Classification , 2019, ICLR.

[22]  Joshua Achiam,et al.  On First-Order Meta-Learning Algorithms , 2018, ArXiv.

[23]  Michael Fink,et al.  Object Classification from a Single Example Utilizing Class Relevance Metrics , 2004, NIPS.

[24]  Lei Wang,et al.  Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[26]  Nir Ailon,et al.  Deep Metric Learning Using Triplet Network , 2014, SIMBAD.

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

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

[29]  Quanming Yao,et al.  Few-shot Learning: A Survey , 2019, ArXiv.

[30]  Xiaogang Wang,et al.  Finding Task-Relevant Features for Few-Shot Learning by Category Traversal , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).