Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators

Although few-shot learning research has advanced rapidly with the help of metalearning, its practical usefulness is still limited because most of them assumed that all meta-training and meta-testing examples came from a single domain. We propose a simple but effective way for few-shot classification in which a task distribution spans multiple domains including ones never seen during meta-training. The key idea is to build a pool of models to cover this wide task distribution and learn to select the best one for a particular task through cross-domain meta-learning. All models in the pool share a base network while each model has a separate modulator to refine the base network in its own way. This framework allows the pool to have representational diversity without losing beneficial domain-invariant features. We verify the effectiveness of the proposed algorithm through experiments on various datasets across diverse domains.

[1]  Johannes Stallkamp,et al.  Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition , 2012, Neural Networks.

[2]  Bernt Schiele,et al.  LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning , 2019, ArXiv.

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

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

[5]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[6]  Jiashi Feng,et al.  Transferable Meta Learning Across Domains , 2018, UAI.

[7]  Andrea Vedaldi,et al.  Efficient Parametrization of Multi-domain Deep Neural Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

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

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

[11]  Andrea Vedaldi,et al.  Learning multiple visual domains with residual adapters , 2017, NIPS.

[12]  Martial Hebert,et al.  Learning to Learn: Model Regression Networks for Easy Small Sample Learning , 2016, ECCV.

[13]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[14]  Mubarak Shah,et al.  UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild , 2012, ArXiv.

[15]  Yongxin Yang,et al.  Episodic Training for Domain Generalization , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Joseph J. Lim,et al.  Toward Multimodal Model-Agnostic Meta-Learning , 2018, ArXiv.

[17]  Seungjin Choi,et al.  MxML: Mixture of Meta-Learners for Few-Shot Classification , 2019, ArXiv.

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

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

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

[21]  Aaron C. Courville,et al.  FiLM: Visual Reasoning with a General Conditioning Layer , 2017, AAAI.

[22]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[23]  Geoffrey E. Hinton,et al.  Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer , 2017, ICLR.

[24]  Subhransu Maji,et al.  Fine-Grained Visual Classification of Aircraft , 2013, ArXiv.

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

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

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

[28]  Dariu Gavrila,et al.  An Experimental Study on Pedestrian Classification , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[30]  Ying Wei,et al.  Hierarchically Structured Meta-learning , 2019, ICML.

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

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

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

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

[35]  Iasonas Kokkinos,et al.  Describing Textures in the Wild , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

[38]  Cordelia Schmid,et al.  Diversity With Cooperation: Ensemble Methods for Few-Shot Classification , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[39]  Donald A. Adjeroh,et al.  Unified Deep Supervised Domain Adaptation and Generalization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).