Abstract | ||
---|---|---|
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. |
Year | Venue | DocType |
---|---|---|
2019 | arXiv: Computer Vision and Pattern Recognition | Journal |
Volume | Citations | PageRank |
abs/1902.10814 | 0 | 0.34 |
References | Authors | |
20 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Da-Cheng Juan | 1 | 195 | 20.47 |
Chun-Ta Lu | 2 | 183 | 15.10 |
zhen li | 3 | 19 | 2.04 |
Futang Peng | 4 | 0 | 0.68 |
Aleksei Timofeev | 5 | 33 | 1.97 |
Yi-Ting Chen | 6 | 0 | 0.68 |
Yaxi Gao | 7 | 0 | 0.34 |
Tom Duerig | 8 | 156 | 6.20 |
Andrew Tomkins | 9 | 9388 | 1401.23 |
Sujith Ravi | 10 | 533 | 33.06 |