Scheduled sampling for one-shot learning via matching network

Abstract Considering human can learn new object successfully from just one sample, one-shot learning, where each visual class just has one labeled sample for training, has attracted more and more attention. In the past years, most researchers achieve one-shot learning by training a matching network to map a small labeled support set and an unlabeled image to its label. The support set is combined by one image with the same label as unlabeled image and few images with other labels generated by random sampling. This random sampling strategy easily generates massive over-easy support sets in which most labels are less relevant to the label of unlabeled image. It leads to the limitation of matching network for one-shot prediction over indistinguishable label sets. For this issue, we propose a novel metric to evaluate the learning difficulty of support set, where this metric jointly considers the semantic diversity and similarity of visual labels. Based on the metric, we introduce a scheduled sampling strategy to train the matching network from easy to difficult. Extensive experimental results on three datasets, including mini-Imagenet, Birds and Flowers, indicate that our method could achieve significant improvements over other previous methods.

[1]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[2]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[3]  Fatih Porikli,et al.  A Unified Approach for Conventional Zero-Shot, Generalized Zero-Shot, and Few-Shot Learning , 2017, IEEE Transactions on Image Processing.

[4]  Tao Zhou An Image Recognition Model Based on Improved Convolutional Neural Network , 2016 .

[5]  Masanori Idesawa,et al.  Recognition of multiple configurations of objects with limited data , 2010, Pattern Recognit..

[6]  James R. Glass,et al.  One-shot learning of generative speech concepts , 2014, CogSci.

[7]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[8]  Babak Saleh,et al.  Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions , 2013, 2013 IEEE International Conference on Computer Vision.

[9]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[10]  Ioannis A. Kakadiaris,et al.  Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification , 2017, Pattern Recognit..

[11]  Sudeep Sarkar,et al.  Conditional distance based matching for one-shot gesture recognition , 2015, Pattern Recognit..

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

[13]  Shiguang Shan,et al.  Self-Paced Curriculum Learning , 2015, AAAI.

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

[15]  Zhihui Li,et al.  Zero-shot event detection via event-adaptive concept relevance mining , 2019, Pattern Recognit..

[16]  Samy Bengio,et al.  Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks , 2015, NIPS.

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

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

[19]  Joshua B. Tenenbaum,et al.  One-shot learning by inverting a compositional causal process , 2013, NIPS.

[20]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[21]  Nanning Zheng,et al.  Deep self-paced learning for person re-identification , 2017, Pattern Recognit..

[22]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[23]  Andrew Zisserman,et al.  Automated Flower Classification over a Large Number of Classes , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[24]  Wu Liu,et al.  DELTA: A deep dual-stream network for multi-label image classification , 2019, Pattern Recognit..

[25]  Zhihui Li,et al.  Diverse fuzzy c-means for image clustering , 2020, Pattern Recognit. Lett..

[26]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

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

[28]  Jakub Konecný,et al.  One-shot-learning gesture recognition using HOG-HOF features , 2014, J. Mach. Learn. Res..

[29]  Daan Wierstra,et al.  Meta-Learning with Memory-Augmented Neural Networks , 2016, ICML.

[30]  Edilson de Aguiar,et al.  Facial expression recognition with Convolutional Neural Networks: Coping with few data and the training sample order , 2017, Pattern Recognit..

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

[32]  Jürgen Schmidhuber,et al.  Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-Improvement , 1997, Machine Learning.

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

[34]  Pengtao Xie,et al.  Diversifying Restricted Boltzmann Machine for Document Modeling , 2015, KDD.

[35]  Sebastian Thrun,et al.  Lifelong Learning Algorithms , 1998, Learning to Learn.