Generative Compositional Augmentations for Scene Graph Prediction
Autor: | Knyazev, Boris, de Vries, Harm, Cangea, Cătălina, Taylor, Graham W., Courville, Aaron, Belilovsky, Eugene |
---|---|
Rok vydání: | 2020 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection of vision and language. We consider a challenging problem of compositional generalization that emerges in this task due to a long tail data distribution. Current scene graph generation models are trained on a tiny fraction of the distribution corresponding to the most frequent compositions, e.g. Comment: ICCV 2021 camera ready. Added more baselines, combining GANs with Neural Motifs and t-sne visualizations. Code is available at https://github.com/bknyaz/sgg |
Databáze: | arXiv |
Externí odkaz: |