Image Deformation Meta-Networks for One-Shot Learning

TL;DR

This paper introduces Image Deformation Meta-Networks, a novel approach combining meta-learning with a deformation sub-network to generate diverse training examples, significantly improving one-shot learning performance on benchmark datasets.

Contribution

It proposes a new meta-learning framework with an image deformation sub-network that synthesizes deformed instances to enhance one-shot learning.

Findings

Significant improvement over state-of-the-art on miniImageNet.

Effective use of deformed images maintaining semantic information.

End-to-end training of meta-learner and deformation network.

Abstract

Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems perform better one-shot learning, i.e., learning concepts from one or few examples. Our key insight is that, while the deformed images may not be visually realistic, they still maintain critical semantic information and contribute significantly to formulating classifier decision boundaries. Inspired by the recent progress of meta-learning, we combine a meta-learner with an image deformation sub-network that produces additional training examples, and optimize both models in an end-to-end manner. The deformation sub-network learns to deform images by fusing a pair of images --- a probe image that keeps the visual content and a gallery image that diversifies the deformations. We demonstrate results on the widely used one-shot learning benchmarks (miniImageNet and ImageNet 1K Challenge datasets), which significantly outperform state-of-the-art approaches. Code is available at https://github.com/tankche1/IDeMe-Net.