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.
@article{arxiv.1902.10814,
title = {Graph-RISE: Graph-Regularized Image Semantic Embedding},
author = {Da-Cheng Juan and Chun-Ta Lu and Zhen Li and Futang Peng and Aleksei Timofeev and Yi-Ting Chen and Yaxi Gao and Tom Duerig and Andrew Tomkins and Sujith Ravi},
journal= {arXiv preprint arXiv:1902.10814},
year = {2019}
}