2017/10/17 by Linjun Zhou, Zhou, Linjun, Peng Cui +7
Computer Science · Mathematics · #Advanced Image and Video Retrieval Techniques #Analogy #Artificial intelligence #Base (topology) #Class (philosophy) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Domain Adaptation and Few-Shot Learning #Embedding #FOS: Computer and information sciences #Function (biology) #Graph #Machine learning #Mathematics #Multiclass classification #Pattern recognition (psychology) #Space (punctuation) #Support vector machine #Theoretical computer science #Visual Attention and Saliency Detection #cs.CV
paper · pdf · doi:10.48550/arxiv.1710.06177
openalex publication_date 2017/10/17 · arxiv created 2019/04/16 · arxiv updated 2019/04/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Humans are far better learners who can learn a new concept very fast with only a few samples compared with machines. The plausible mystery making the difference is two fundamental learning mechanisms: learning to learn and learning by analogy. In this paper, we attempt to investigate a new human-like learning method by organically combining these two mechanisms. In particular, we study how to generalize the classification parameters from previously learned concepts to a new concept. we first propose a novel Visual Analogy Graph Embedded Regression (VAGER) model to jointly learn a low-dimensional embedding space and a linear mapping function from the embedding space to classification parameters for base classes. We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes and derive the classification parameters for the new class. We conduct extensive experiments on ImageNet dataset and the results show that our method could consistently and significantly outperform state-of-the-art baselines.