Making a scene – using GAN generated scenes to test the role of real-world co-occurence statistics and hierarchical feature spaces in scene understanding.

Author:

Kallmayer Aylin1ORCID,Võ Melissa2

Affiliation:

1. Goethe University

2. Goethe-University Frankfurt

Abstract

Abstract

Our visual surroundings are highly complex. Despite this, we understand and navigate them effortlessly. This requires a complex series of transformations resulting in representations that not only span low- to high-level visual features (e.g., contours, textures, object parts and objects), but likely also reflect co-occurrence statistics of objects in real-world scenes. Here, so-called anchor objects reflect clustering statistics in real-world scenes, anchoring predictions towards frequently co-occuring smaller objects, while so-called diagnostic objects predict the larger semantic context. We investigate which of these properties underly scene understanding across two dimensions – realism and categorisation – using scenes generated from Generative Adversarial Networks (GANs) which naturally vary along these dimensions. We show that anchor objects and mainly high-level features extracted from a range of pre-trained deep neural networks (DNNs) drove realism both at first glance and after initial processing. Categorisation performance was mainly determined by diagnostic objects, regardless of realism and DNN features, also at first glance and after initial processing. Our results are testament to the visual system’s ability to pick up on reliable, category specific sources of information that are flexible towards disturbances across the visual feature hierarchy.

Publisher

Springer Science and Business Media LLC

Reference66 articles.

1. The Briefest of Glances: The Time Course of Natural Scene Understanding;Greene MR;Psychol Sci,2009

2. Human gaze control during real-world scene perception;Henderson JM;Trends in Cognitive Sciences,2003

3. Rapid conceptual identification of sequentially presented pictures;Intraub H;Journal of Experimental Psychology: Human Perception and Performance,1981

4. Diagnostic Colors Mediate Scene Recognition;Oliva A;Cognitive Psychology,2000

5. Detecting meaning in RSVP at 13 ms per picture;Potter MC;Atten Percept Psychophys,2014

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3