Triplet-Aware Scene Graph Embeddings

Brigit Schroeder, Subarna Tripathi, Hanlin Tang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0


Scene graphs have become an important form of structured knowledge for tasks such as visual relation detection, visual question answering, and image retrieval. While visualizing and interpreting word embeddings is well understood, scene graph embeddings have not been fully explored. In this work, we train scene graph embeddings in a layout generation task with varying forms of supervision, specifically introducing triplet supervision and data augmentation. We see a significant performance increase in both metrics that measure the goodness of layout prediction, mean intersection-over-union (mIoU) (52.3% vs. 49.2%) and relation score (61.7% vs. 54.1%), after the addition of triplet supervision and data augmentation. To understand how these different methods effect the scene graph representation, we apply several new visualization and evaluation methods to explore the evolution of the scene graph embedding. We find that triplet supervision significantly improves the embedding separability, which is highly correlated with performance of the layout prediction model.

Related Material

author = {Schroeder, Brigit and Tripathi, Subarna and Tang, Hanlin},
title = {Triplet-Aware Scene Graph Embeddings},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}