Prototype Rectification for Few-Shot Learning

Few-shot learning requires to recognize novel classes with scarce labeled data. Prototypical network is useful in existing researches, however, training on narrow-size distribution of scarce data usually tends to get biased prototypes. In this paper, we figure out two key influencing factors of the process: the intra-class bias and the cross-class bias. We then propose a simple yet effective approach for prototype rectification in transductive setting. The approach utilizes label propagation to diminish the intra-class bias and feature shifting to diminish the cross-class bias. We also conduct theoretical analysis to derive its rationality as well as the lower bound of the performance. Effectiveness is shown on three few-shot benchmarks. Notably, our approach achieves state-of-the-art performance on both miniImageNet (70.31% on 1-shot and 81.89% on 5-shot) and tieredImageNet (78.74% on 1-shot and 86.92% on 5-shot).

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

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

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

[4]  Joan Bruna,et al.  Few-Shot Learning with Graph Neural Networks , 2017, ICLR.

[5]  Patrick Pérez,et al.  Boosting Few-Shot Visual Learning With Self-Supervision , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[7]  Hugo Larochelle,et al.  Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples , 2019, ICLR.

[8]  Joshua B. Tenenbaum,et al.  Meta-Learning for Semi-Supervised Few-Shot Classification , 2018, ICLR.

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

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

[11]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[12]  Wei Shen,et al.  Few-Shot Image Recognition by Predicting Parameters from Activations , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Tsendsuren Munkhdalai,et al.  Rapid Adaptation with Conditionally Shifted Neurons , 2017, ICML.

[14]  Luc Van Gool,et al.  Deep Domain Adaptation by Geodesic Distance Minimization , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[15]  Luca Bertinetto,et al.  Meta-learning with differentiable closed-form solvers , 2018, ICLR.

[16]  S. Rice.  The expected value of the ratio of correlated random variables , 2015 .

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

[18]  Bernt Schiele,et al.  Learning to Self-Train for Semi-Supervised Few-Shot Classification , 2019, NeurIPS.

[19]  Joshua B. Tenenbaum,et al.  Infinite Mixture Prototypes for Few-Shot Learning , 2019, ICML.

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

[21]  Pieter Abbeel,et al.  A Simple Neural Attentive Meta-Learner , 2017, ICLR.

[22]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[23]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[24]  Stefano Soatto,et al.  A Baseline for Few-Shot Image Classification , 2019, ICLR.

[25]  Subhransu Maji,et al.  Meta-Learning With Differentiable Convex Optimization , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

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

[29]  Razvan Pascanu,et al.  Meta-Learning with Latent Embedding Optimization , 2018, ICLR.

[30]  Paul A. Viola,et al.  Learning from one example through shared densities on transforms , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[31]  Hang Li,et al.  Meta-SGD: Learning to Learn Quickly for Few Shot Learning , 2017, ArXiv.

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

[33]  Eunho Yang,et al.  Learning to Propagate Labels: Transductive Propagation Network for Few-Shot Learning , 2018, ICLR.

[34]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[35]  Sebastian Nowozin,et al.  Optimal Decisions from Probabilistic Models: The Intersection-over-Union Case , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[37]  Taesup Kim,et al.  Edge-Labeling Graph Neural Network for Few-Shot Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[40]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

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

[42]  J. Schulman,et al.  Reptile: a Scalable Metalearning Algorithm , 2018 .