Learning Fine-grained Image Similarity with Deep Ranking

• DOI: 10.48550/arxiv.1404.4661
• Publication Date: 2014-01-01
• Authors: Jiang Wang; Yang Song; Thomas Leung; Chuck Rosenberg; Jinbin Wang; James Philbin; Bo Chen; Ying Wu
• Keywords: Similarity (geometry); Similarity learning

Learning fine-grained image similarity is a challenging task. It needs to capture between-class and within-class differences. This paper proposes deep ranking model that employs learning techniques learn metric directly from images.It has higher capability than models based on hand-crafted features. A novel multiscale network structure been developed describe the images effectively. An efficient triplet sampling algorithm proposed with distributed asynchronized stochastic gradient. Extensive experiments show outperforms visual features classification models.