Generative Adversarial Residual Pairwise Networks for One Shot Learning

Abstract

Deep neural networks achieve unprecedented performance levels over many tasks and scale well with large quantities of data, but performance in the low-data regime and tasks like one shot learning still lags behind. While recent work suggests many hypotheses from better optimization to more complicated network structures, in this work we hypothesize that having a learnable and more expressive similarity objective is an essential missing component. Towards overcoming that, we propose a network design inspired by deep residual networks that allows the efficient computation of this more expressive pairwise similarity objective. Further, we argue that regularization is key in learning with small amounts of data, and propose an additional generator network based on the Generative Adversarial Networks where the discriminator is our residual pairwise network. This provides a strong regularizer by leveraging the generated data samples. The proposed model can generate plausible variations of exemplars over unseen classes and outperforms strong discriminative baselines for few shot classification tasks. Notably, our residual pairwise network design outperforms previous state-of-theart on the challenging mini-Imagenet dataset for one shot learning by getting over 55% accuracy for the 5-way classification task over unseen classes.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Deep Residual Learning for Image Recognition
• Wide Residual Networks
• Improved Techniques for Training GANs
• Matching Networks for One Shot Learning
• Learning in Implicit Generative Models
• Towards a Neural Statistician
• Attentive Recurrent Comparators
• Metric Learning with Adaptive Density Discrimination

Cited by in corpus (15)

• Few-Shot Learning with Graph Neural Networks
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• Meta-Learning Requires Meta-Augmentation
• DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
• Meta-Transfer Learning for Few-Shot Learning
• Large Margin Few-Shot Learning
• Few-shot Classification via Adaptive Attention
• Generative One-Shot Face Recognition
• DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
• Learning from similarity and information extraction from structured documents
• AgileNet: Lightweight Dictionary-based Few-shot Learning
• A Novel BiLevel Paradigm for Image-to-Image Translation
• A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning
• Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
• Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts