Name
Abstract | ||
|---|---|---|
In this paper we investigate the problems of class imbalance and irrelevant relationships in Visual Relationship Detection (VRD). State-of-the-art deep VRD models still struggle to predict uncommon classes, limiting their applicability. Moreover, many methods are incapable of properly filtering out background relationships while predicting relevant ones. Although these problems are very apparent, they have both been overlooked so far. We analyse why this is the case and propose modifications to both model and training to alleviate the aforementioned issues, as well as suggesting new measures to complement existing ones and give a more holistic picture of the efficacy of a model. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/IJCNN.2019.8851814 | 2019 International Joint Conference on Neural Networks (IJCNN) |
Keywords | Field | DocType |
class imbalance,background filtering,background relationships,visual relationship detection,VRD models | Computer science,Filter (signal processing),Artificial intelligence,Machine learning,Limiting | Journal |
Volume | ISSN | ISBN |
abs/1903.08456 | 2161-4393 | 978-1-7281-1986-1 |
Citations | PageRank | References |
0 | 0.34 | 6 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alessio Sarullo | 1 | 0 | 0.68 |
| Tingting Mu | 2 | 19 | 4.98 |