Image Deformation Meta-Networks for One-Shot Learning

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.

Oral at CVPR2019. Code is available at https://github.com/tankche1/IDeMe-Net

References in corpus (8)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Semi-Supervised Learning with Ladder Networks
• Few-Shot Learning with Graph Neural Networks
• Deep Meta-Learning: Learning to Learn in the Concept Space
• Few-Shot Object Recognition from Machine-Labeled Web Images

Cited by in corpus (11)

• Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
• Rectifying the Shortcut Learning of Background for Few-Shot Learning
• Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
• Adversarial Feature Hallucination Networks for Few-Shot Learning
• Instance Credibility Inference for Few-Shot Learning
• Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
• Machine learning with limited data
• Semantic Compositional Learning for Low-shot Scene Graph Generation
• Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
• Class Interference Regularization
• Diversity Transfer Network for Few-Shot Learning