Improving One-Shot Learning through Fusing Side Information

Abstract

Deep Neural Networks (DNNs) often struggle with one-shot learning where we have only one or a few labeled training examples per category. In this paper, we argue that by using side information, we may compensate the missing information across classes. We introduce two statistical approaches for fusing side information into data representation learning to improve one-shot learning. First, we propose to enforce the statistical dependency between data representations and multiple types of side information. Second, we introduce an attention mechanism to efficiently treat examples belonging to the 'lots-of-examples' classes as quasi-samples (additional training samples) for 'one-example' classes. We empirically show that our learning architecture improves over traditional softmax regression networks as well as state-of-the-art attentional regression networks on one-shot recognition tasks.

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Robust Visual-Semantic Embeddings

Cited by in corpus (8)

• Few-shot classification in Named Entity Recognition Task
• Learning from Few Samples: A Survey
• MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samples
• SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning
• What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
• Modeling the Biological Pathology Continuum with HSIC-regularized Wasserstein Auto-encoders
• Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition
• Few Shot Learning With No Labels