Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning

Abstract

Few-shot learning aims to classify unseen classes with a few training examples. While recent works have shown that standard mini-batch training with a carefully designed training strategy can improve generalization ability for unseen classes, well-known problems in deep networks such as memorizing training statistics have been less explored for few-shot learning. To tackle this issue, we propose self-augmentation that consolidates self-mix and self-distillation. Specifically, we exploit a regional dropout technique called self-mix, in which a patch of an image is substituted into other values in the same image. Then, we employ a backbone network that has auxiliary branches with its own classifier to enforce knowledge sharing. Lastly, we present a local representation learner to further exploit a few training examples for unseen classes. Experimental results show that the proposed method outperforms the state-of-the-art methods for prevalent few-shot benchmarks and improves the generalization ability.

arXiv commentThe first two authors contributed equally to this work

References in corpus (19)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• mixup: Beyond Empirical Risk Minimization
• Improved Regularization of Convolutional Neural Networks with Cutout
• On Calibration of Modern Neural Networks
• Matching Networks for One Shot Learning
• When Does Label Smoothing Help?
• Meta-Learning for Semi-Supervised Few-Shot Classification
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• Manifold Mixup: Better Representations by Interpolating Hidden States
• Regularizing Neural Networks by Penalizing Confident Output Distributions
• Knowledge Distillation by On-the-Fly Native Ensemble
• Exploring Generalization in Deep Learning
• A Closer Look at Few-shot Classification
• Meta-learning with differentiable closed-form solvers
• Cross Attention Network for Few-shot Classification
• Entropy-SGD: Biasing Gradient Descent Into Wide Valleys

Cited by in corpus (3)

• Towards Understanding Label Smoothing
• Data Augmentation for Meta-Learning
• Few-shot Learning with LSSVM Base Learner and Transductive Modules