Graphs are a useful abstraction of image content. Not only can graphs represent details about individual objects in a scene but they can capture the interactions between pairs of objects. We present a method for training a convolutional neural network such that it takes in an input image and produces a full graph definition. This is done end-to-end in a single stage with the use of associative embeddings. The network learns to simultaneously identify all of the elements that make up a graph and piece them together. We benchmark on the Visual Genome dataset, and demonstrate state-of-the-art performance on the challenging task of scene graph generation.
|Original language||English (US)|
|Title of host publication||31st Annual Conference on Neural Information Processing Systems (NIPS)|
|Publisher||NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)|
|State||Published - 2017|