Diversity With Cooperation: Ensemble Methods for Few-Shot Classification

Few-shot classification consists of learning a predictive model that is able to effectively adapt to a new class, given only a few annotated samples. To solve this challenging problem, meta-learning has become a popular paradigm that advocates the ability to ``learn to adapt''. Recent works have shown, however, that simple learning strategies without meta-learning could be competitive. In this paper, we go a step further and show that by addressing the fundamental high-variance issue of few-shot learning classifiers, it is possible to significantly outperform current meta-learning techniques. Our approach consists of designing an ensemble of deep networks to leverage the variance of the classifiers, and introducing new strategies to encourage the networks to cooperate, while encouraging prediction diversity. Evaluation is conducted on the mini-ImageNet, tiered-ImageNet and CUB datasets, where we show that even a single network obtained by distillation yields state-of-the-art results.

[1]  L. Breiman.  Heuristics of instability and stabilization in model selection , 1996 .

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

[3]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[4]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Julien Mairal,et al.  A Kernel Perspective for Regularizing Deep Neural Networks , 2018, ICML.

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

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

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

[9]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[10]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

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

[12]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[13]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[14]  Julien Mairal,et al.  BlitzNet: A Real-Time Deep Network for Scene Understanding , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Andrew Zisserman,et al.  Multi-task Self-Supervised Visual Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[18]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

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

[20]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

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

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

[23]  Gabriela Csurka,et al.  Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[26]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Yuichi Yoshida,et al.  Spectral Norm Regularization for Improving the Generalizability of Deep Learning , 2017, ArXiv.

[28]  Matthijs Douze,et al.  Deep Clustering for Unsupervised Learning of Visual Features , 2018, ECCV.

[29]  Nikos Komodakis,et al.  Unsupervised Representation Learning by Predicting Image Rotations , 2018, ICLR.

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

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

[32]  Geoffrey E. Hinton,et al.  Large scale distributed neural network training through online distillation , 2018, ICLR.

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

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

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

[36]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

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