Relational Generalized Few-Shot Learning

Transferring learned models to novel tasks is a challenging problem, particularly if only very few labeled examples are available. Although this few-shot learning setup has received a lot of attention recently, most proposed methods focus on discriminating novel classes only. Instead, we consider the extended setup of generalized few-shot learning (GFSL), where the model is required to perform classification on the joint label space consisting of both previously seen and novel classes. We propose a graph-based framework that explicitly models relationships between all seen and novel classes in the joint label space. Our model Graph-convolutional Global Prototypical Networks (GcGPN) incorporates these inter-class relations using graph-convolution in order to embed novel class representations into the existing space of previously seen classes in a globally consistent manner. Our approach ensures both fast adaptation and global discrimination, which is the major challenge in GFSL. We demonstrate the benefits of our model on two challenging benchmark datasets.

[1]  Jinhui Tang,et al.  Few-Shot Image Recognition With Knowledge Transfer , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[2]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

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

[4]  Razvan Pascanu,et al.  A simple neural network module for relational reasoning , 2017, NIPS.

[5]  R. Zemel,et al.  Few-shot Learning for Free by Modelling Global Class Structure , 2018 .

[6]  Amos J. Storkey,et al.  How to train your MAML , 2018, ICLR.

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

[8]  Bernt Schiele,et al.  F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[10]  Chenrui Zhang,et al.  TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning , 2019, ACM Multimedia.

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

[12]  Christoph H. Lampert,et al.  Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[14]  Wei-Lun Chao,et al.  An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild , 2016, ECCV.

[15]  Ruslan Salakhutdinov,et al.  Learning Robust Visual-Semantic Embeddings , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[17]  Trevor Darrell,et al.  Generalized Zero-Shot Learning via Aligned Variational Autoencoders , 2019, CVPR Workshops.

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

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

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

[21]  Samy Bengio,et al.  Zero-Shot Learning by Convex Combination of Semantic Embeddings , 2013, ICLR.

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

[23]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[24]  Aurko Roy,et al.  Learning to Remember Rare Events , 2017, ICLR.

[25]  Shimon Ullman,et al.  Cross-generalization: learning novel classes from a single example by feature replacement , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[27]  Kun Duan,et al.  Discovering localized attributes for fine-grained recognition , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Nuno Vasconcelos,et al.  Semantically Consistent Regularization for Zero-Shot Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Guy Van den Broeck,et al.  A Semantic Loss Function for Deep Learning with Symbolic Knowledge , 2017, ICML.

[30]  Ted Pedersen,et al.  WordNet::Similarity - Measuring the Relatedness of Concepts , 2004, NAACL.

[31]  Max Welling,et al.  Graph Convolutional Matrix Completion , 2017, ArXiv.

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

[33]  Ruslan Salakhutdinov,et al.  Improving One-Shot Learning through Fusing Side Information , 2017, ArXiv.

[34]  Bernhard Schölkopf,et al.  Discriminative k-shot learning using probabilistic models , 2017, ArXiv.

[35]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

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

[37]  Abhinav Gupta,et al.  Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[38]  Piyush Rai,et al.  A Simple Exponential Family Framework for Zero-Shot Learning , 2017, ECML/PKDD.

[39]  Nikos Komodakis,et al.  Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Tao Xiang,et al.  Few-Shot Learning With Global Class Representations , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[42]  Bartunov Sergey,et al.  Meta-Learning with Memory-Augmented Neural Networks , 2016 .

[43]  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).

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

[45]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[46]  Sebastian Thrun,et al.  Is Learning The n-th Thing Any Easier Than Learning The First? , 1995, NIPS.

[47]  Xiaogang Wang,et al.  Finding Task-Relevant Features for Few-Shot Learning by Category Traversal , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  Sebastian Nowozin,et al.  Meta-Learning Probabilistic Inference for Prediction , 2018, ICLR.

[49]  Cordelia Schmid,et al.  Label-Embedding for Image Classification , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[50]  Zhiwu Lu,et al.  Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[52]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[53]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[54]  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).

[55]  Marc'Aurelio Ranzato,et al.  DeViSE: A Deep Visual-Semantic Embedding Model , 2013, NIPS.