TLRM: Task-level Relation Module for GNN-based Few-Shot Learning

Recently, graph neural networks (GNNs) have shown powerful ability to handle few-shot classification problem, which aims at classifying unseen samples when trained with limited labeled samples per class. GNN-based few-shot learning architectures mostly replace traditional metric with a learnable GNN. In the GNN, the nodes are set as the samples' embedding, and the relationship between two connected nodes can be obtained by a network, the input of which is the difference of their embedding features. We consider this method of measuring relation of samples only models the sample-to-sample relation, while neglects the specificity of different tasks. That is, this method of measuring relation does not take the task-level information into account. To this end, we propose a new relation measure method, namely the task-level relation module (TLRM), to explicitly model the task-level relation of one sample to all the others. The proposed module captures the relation representations between nodes by considering the sample-to-task instead of sample-to-sample embedding features. We conducted extensive experiments on four benchmark datasets: mini-ImageNet, tiered-ImageNet, CUB-200-2011, and CIFAR-FS. Experimental results demonstrate that the proposed module is effective for GNN-based few-shot learning.

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

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

[3]  Jie Cao,et al.  BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification , 2021, IEEE Transactions on Image Processing.

[4]  Luca Bertinetto,et al.  Meta-learning with differentiable closed-form solvers , 2018, ICLR.

[5]  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).

[6]  Xilin Chen,et al.  Cross Attention Network for Few-shot Classification , 2019, NeurIPS.

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

[8]  Mubarak Shah,et al.  Task Agnostic Meta-Learning for Few-Shot Learning , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Hong Yu,et al.  Meta Networks , 2017, ICML.

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

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

[12]  Kui Jia,et al.  PARN: Position-Aware Relation Networks for Few-Shot Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[13]  Jiebo Luo,et al.  Distribution Consistency Based Covariance Metric Networks for Few-Shot Learning , 2019, AAAI.

[14]  Yan Zheng,et al.  Principal characteristic networks for few-shot learning , 2019, J. Vis. Commun. Image Represent..

[15]  Yi-Zhe Song,et al.  The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification , 2020, IEEE Transactions on Image Processing.

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

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

[18]  Feiyue Huang,et al.  LGM-Net: Learning to Generate Matching Networks for Few-Shot Learning , 2019, ICML.

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

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

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

[22]  Philip H. S. Torr,et al.  Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[25]  Feiyue Huang,et al.  Learning Dynamic Alignment via Meta-filter for Few-shot Learning , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[27]  Shaoguo Wen,et al.  Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification , 2020, ArXiv.

[28]  Yunming Ye,et al.  Prototype Completion with Primitive Knowledge for Few-Shot Learning , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Ling Yang,et al.  DPGN: Distribution Propagation Graph Network for Few-Shot Learning , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Stan Matwin,et al.  Learning to Learn with Conditional Class Dependencies , 2018, ICLR.

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

[32]  Lei Wang,et al.  Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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