papers AI Learner
The Github is limit! Click to go to the new site.

Revisiting Visual Grounding

2019-04-03
Erik Conser, Kennedy Hahn, Chandler M. Watson, Melanie Mitchell

Abstract

We revisit a particular visual grounding method: the “Image Retrieval Using Scene Graphs” (IRSG) system of Johnson et al. (2015). Our experiments indicate that the system does not effectively use its learned object-relationship models. We also look closely at the IRSG dataset, as well as the widely used Visual Relationship Dataset (VRD) that is adapted from it. We find that these datasets exhibit biases that allow methods that ignore relationships to perform relatively well. We also describe several other problems with the IRSG dataset, and report on experiments using a subset of the dataset in which the biases and other problems are removed. Our studies contribute to a more general effort: that of better understanding what machine learning methods that combine language and vision actually learn and what popular datasets actually test.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.02225

PDF

http://arxiv.org/pdf/1904.02225


Similar Posts

Comments