Enhancing Few-Shot Image Classification with Unlabelled Examples

We propose a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance. Our approach combines a regularized Mahalanobis-distance-based soft k-means clustering procedure with a modified state of the art neural adaptive feature extractor to achieve improved test-time classification accuracy using unlabelled data. We evaluate our method on transductive few-shot learning tasks, in which the goal is to jointly predict labels for query (test) examples given a set of support (training) examples. We achieve new state of the art performance on Meta-Dataset, and produce competitive results on mini- and tiered-ImageNet benchmarks.

[1]  V. Vanitha,et al.  A Survey on Image Classification and Activity Recognition using Deep Convolutional Neural Network Architecture , 2017, 2017 Ninth International Conference on Advanced Computing (ICoAC).

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

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

[4]  Sebastian Nowozin,et al.  Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes , 2019, NeurIPS.

[5]  Johannes Stallkamp,et al.  Detection of traffic signs in real-world images: The German traffic sign detection benchmark , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

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

[7]  Mohammad Norouzi,et al.  Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One , 2019, ICLR.

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

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

[10]  Chunyan Miao,et al.  A Survey of Zero-Shot Learning , 2019, ACM Trans. Intell. Syst. Technol..

[11]  Ruigang Yang,et al.  Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Yonghong Tian,et al.  Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

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

[15]  Quanming Yao,et al.  Few-shot Learning: A Survey , 2019, ArXiv.

[16]  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).

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

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

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

[20]  Leonid Sigal,et al.  Improved Few-Shot Visual Classification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Pieter Abbeel,et al.  Meta-Learning with Temporal Convolutions , 2017, ArXiv.

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

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

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

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

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

[27]  Deva Ramanan,et al.  Local Distance Functions: A Taxonomy, New Algorithms, and an Evaluation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[30]  Yi Yang,et al.  Transductive Propagation Network for Few-shot Learning , 2018, ArXiv.

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

[32]  Julien Mairal,et al.  Selecting Relevant Features from a Multi-domain Representation for Few-Shot Classification , 2020, ECCV.

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

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

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

[36]  Marc Sebban,et al.  A Survey on Metric Learning for Feature Vectors and Structured Data , 2013, ArXiv.

[37]  Volodymyr Melnykov,et al.  On K-means algorithm with the use of Mahalanobis distances , 2014 .

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

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

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

[41]  Søren Hauberg,et al.  A Geometric take on Metric Learning , 2012, NIPS.

[42]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

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

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

[45]  Jose Dolz,et al.  Semi-supervised few-shot learning for medical image segmentation , 2020, ArXiv.