Self-Denoising Neural Networks for Few Shot Learning

In this paper, we introduce a new architecture for few shot learning, the task of teaching a neural network from as few as one or five labeled examples. Inspired by the theoretical results of Alaine et al. that Denoising Autoencoders refine features to lie closer to the true data manifold, we present a new training scheme that adds noise at multiple stages of an existing neural architecture while simultaneously learning to be robust to this added noise. This architecture, which we call a Self-Denoising Neural Network (SDNN), can be applied easily to most modern convolutional neural architectures, and can be used as a supplement to many existing few-shot learning techniques. We empirically show that SDNNs out-perform previous state-of-the-art methods for few shot image recognition using the Wide-ResNet architecture on the miniImageNet, tieredImageNet, and CIFAR-FS few shot learning datasets. We also perform a series of ablation experiments to empirically justify the construction of the SDNN architecture. Finally, we show that SDNNs even improve few shot performance on the task of human action detection in video using experiments on the ActEV SDL Surprise Activities challenge.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[3]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[4]  Matthew A. Brown,et al.  Low-Shot Learning with Imprinted Weights , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Yoshua Bengio,et al.  What regularized auto-encoders learn from the data-generating distribution , 2012, J. Mach. Learn. Res..

[6]  Kellie Corona,et al.  MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection , 2020, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV).

[7]  Patrick Pérez,et al.  Boosting Few-Shot Visual Learning With Self-Supervision , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

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

[10]  Yannis Avrithis,et al.  Dense Classification and Implanting for Few-Shot Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[12]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[13]  Subhransu Maji,et al.  When Does Self-supervision Improve Few-shot Learning? , 2020, ECCV.

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

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

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

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

[18]  Joseph J. Lim,et al.  Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation , 2019, NeurIPS.

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

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

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

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

[23]  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).

[24]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

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

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

[27]  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).

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

[29]  Yue Wang,et al.  Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? , 2020, ECCV.

[30]  Hung-Yu Tseng,et al.  Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation , 2020, ICLR.

[31]  Carlos D. Castillo,et al.  Activity Detection in Untrimmed Videos Using Chunk-based Classifiers , 2020, 2020 IEEE Winter Applications of Computer Vision Workshops (WACVW).

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

[33]  Jun-Cheng Chen,et al.  A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos , 2018, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV).

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

[35]  Bharath Hariharan,et al.  Low-Shot Visual Recognition by Shrinking and Hallucinating Features , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

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

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

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

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

[40]  Andrew Zisserman,et al.  Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Martial Hebert,et al.  Low-Shot Learning from Imaginary Data , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.