Graph-RISE: Graph-Regularized Image Semantic Embedding

Autor:	Juan, Da-Cheng, Lu, Chun-Ta, Li, Zhen, Peng, Futang, Timofeev, Aleksei, Chen, Yi-Ting, Gao, Yaxi, Duerig, Tom, Tomkins, Andrew, Ravi, Sujith
Rok vydání:	2019
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering. In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to train embeddings to discriminate an unprecedented O(40M) ultra-fine-grained semantic labels. Graph-RISE outperforms state-of-the-art image embedding algorithms on several evaluation tasks, including image classification and triplet ranking. We provide case studies to demonstrate that, qualitatively, image retrieval based on Graph-RISE effectively captures semantics and, compared to the state-of-the-art, differentiates nuances at levels that are closer to human-perception. Comment: 9 pages, 7 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1902.10814 Zobrazit plný text záznamu View this record from Arxiv