Learning Fine-Grained Image Similarity with Deep Ranking
CVPR(2014)
摘要
Learning fine-grained image similarity is a challenging task. It needs to capture between-class and within-class image differences. This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images. It has higher learning capability than models based on hand-crafted features. A novel multiscale network structure has been developed to describe the images effectively. An efficient triplet sampling algorithm is also proposed to learn the model with distributed asynchronized stochastic gradient. Extensive experiments show that the proposed algorithm outperforms models based on hand-crafted visual features and deep classification models.
更多查看译文
关键词
learning fine-grained image similarity,stochastic processes,learning (artificial intelligence),multiscale network structure,deep ranking,image differences,deep learning techniques,image sampling,gradient methods,triplet sampling algorithm,distributed asynchronized stochastic gradient,learning artificial intelligence,neural networks,computer architecture,computational modeling,semantics,training data,visualization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络