Skip to main content

SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

Author(s): Yang, Kaiyu; Russakovsky, Olga; Deng, Jia

To refer to this page use:
Abstract: Understanding the spatial relations between objects in images is a surprisingly challenging task. A chair may be "behind" a person even if it appears to the left of the person in the image (depending on which way the person is facing). Two students that appear close to each other in the image may not in fact be "next to" each other if there is a third student between them. We introduce SpatialSense, a dataset specializing in spatial relation recognition which captures a broad spectrum of such challenges, allowing for proper benchmarking of computer vision techniques. SpatialSense is constructed through adversarial crowdsourcing, in which human annotators are tasked with finding spatial relations that are difficult to predict using simple cues such as 2D spatial configuration or language priors. Adversarial crowdsourcing significantly reduces dataset bias and samples more interesting relations in the long tail compared to existing datasets. On SpatialSense, state-of-the-art recognition models perform comparably to simple baselines, suggesting that they rely on straightforward cues instead of fully reasoning about this complex task. The SpatialSense benchmark provides a path forward to advancing the spatial reasoning capabilities of computer vision systems. The dataset and code are available at
Publication Date: 2019
Citation: Yang, Kaiyu, Olga Russakovsky, and Jia Deng. "SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition." In IEEE International Conference on Computer Vision (ICCV), pp. 2051-2060. 2019. doi: 10.1109/ICCV.2019.00214
ISSN: 1550-5499
EISSN: 2380-7504
Pages: 2051-2060
Type of Material: Conference Article
Journal/Proceeding Title: IEEE International Conference on Computer Vision (ICCV)
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.