Incremental Meta-Learning via Indirect Discriminant Alignment

Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large dataset and a testing phase, where the meta-learner leverages its learnt internal representation for a specific few-shot task involving classes which were not seen during the meta-training phase. To the best of our knowledge, all such meta-learning methods use a single base dataset for meta-training to sample tasks from and do not adapt the algorithm after meta-training. This strategy may not scale to real-world use-cases where the meta-learner does not potentially have access to the full meta-training dataset from the very beginning and we need to update the meta-learner in an incremental fashion when additional training data becomes available. Through our experimental setup, we develop a notion of incremental learning during the meta-training phase of meta-learning and propose a method which can be used with multiple existing metric-based meta-learning algorithms. Experimental results on benchmark dataset show that our approach performs favorably at test time as compared to training a model with the full meta-training set and incurs negligible amount of catastrophic forgetting

[1]  Sebastian Thrun,et al.  Learning to Learn , 1998, Springer US.

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

[3]  Stefano Soatto,et al.  Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[4]  Richard J. Mammone,et al.  Meta-neural networks that learn by learning , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[5]  Pietro Perona,et al.  The Devil is in the Tails: Fine-grained Classification in the Wild , 2017, ArXiv.

[6]  Dragomir Anguelov,et al.  Capturing Long-Tail Distributions of Object Subcategories , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

[9]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[12]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[13]  R. French Catastrophic forgetting in connectionist networks , 1999, Trends in Cognitive Sciences.

[14]  Mennatullah Siam,et al.  Adaptive Masked Proxies for Few-Shot Segmentation , 2019 .

[15]  Subhransu Maji,et al.  Task2Vec: Task Embedding for Meta-Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[17]  Thomas L. Griffiths,et al.  Reconciling meta-learning and continual learning with online mixtures of tasks , 2018, NeurIPS.

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

[19]  Sergey Levine,et al.  Trust Region Policy Optimization , 2015, ICML.

[20]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[22]  Marco Pavone,et al.  Continuous Meta-Learning without Tasks , 2020, NeurIPS.

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

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

[25]  Rich Caruana,et al.  Do Deep Nets Really Need to be Deep? , 2013, NIPS.

[26]  Sergey Levine,et al.  Online Meta-Learning , 2019, ICML.

[27]  Marc'Aurelio Ranzato,et al.  Efficient Lifelong Learning with A-GEM , 2018, ICLR.

[28]  Yee Whye Teh,et al.  Progress & Compress: A scalable framework for continual learning , 2018, ICML.

[29]  Martial Hebert,et al.  Learning to Model the Tail , 2017, NIPS.

[30]  Quoc V. Le,et al.  DropBlock: A regularization method for convolutional networks , 2018, NeurIPS.

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

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

[33]  Guiguang Ding,et al.  Incremental Few-Shot Learning for Pedestrian Attribute Recognition , 2019, IJCAI.

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

[35]  Renjie Liao,et al.  Incremental Few-Shot Learning with Attention Attractor Networks , 2018, NeurIPS.

[36]  Marc'Aurelio Ranzato,et al.  Gradient Episodic Memory for Continual Learning , 2017, NIPS.

[37]  Mennatullah Siam,et al.  Adaptive Masked Weight Imprinting for Few-Shot Segmentation , 2019, ArXiv.

[38]  Yoshua Bengio,et al.  On the Optimization of a Synaptic Learning Rule , 2007 .

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

[40]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.