@inproceedings{b8f75ee6af2d41de8bac022260922f04,
title = "Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction",
abstract = "Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple interrelated objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing such effects is structured prediction, which optimizes over complex labels, while modeling within-label interactions. However, it is unclear what principles should guide the design of a structured prediction model that utilizes the power of deep learning components. Here we propose a design principle for such architectures that follows from a natural requirement of permutation invariance. We prove a necessary and sufficient characterization for architectures that follow this invariance, and discuss its implication on model design. Finally, we show that the resulting model achieves new state-of-the-art results on the Visual Genome scene-graph labeling benchmark, outperforming all recent approaches.",
author = "Roei Herzig and Moshiko Raboh and Gal Chechik and Jonathan Berant and Amir Globerson",
year = "2018",
language = "אנגלית",
series = "Advances in Neural Information Processing Systems",
publisher = "Curran Associates, Inc.",
editor = "S. Bengio and Wallach, {H. } and H. Larochelle and K. Grauman and {Cesa-Bianchi }, {N. } and Garnett, {R. }",
booktitle = "ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018)",
note = "32nd Conference on Neural Information Processing Systems, NeurIPS 2018 ; Conference date: 02-12-2018 Through 08-12-2018",
}