Recognition of natural scenes from global properties: Seeing the forest without representing the trees

By Michelle R. Greene, Aude Oliva. Cognitive Psychology, 2008

476 citations recorded by the source corpus.

Human observers are able to rapidly and accurately categorize natural scenes, but the representation mediating this feat is still unknown. Here we propose a framework of rapid scene categorization that does not segment a scene into objects and instead uses a vocabulary of global, ecological properties that describe spatial and functional aspects of scene space (such as navigability or mean depth). In Experiment 1, we obtained ground truth rankings on global properties for use in Experiments 2–4. To what extent do human observers use global property information when rapidly categorizing natural scenes? In Experiment 2, we found that global property resemblance was a strong predictor of both false alarm rates and reaction times in a rapid scene categorization experiment. To what extent is global property information alone a sufficient predictor of rapid natural scene categorization? In Experiment 3, we found that the performance of a classifier representing only these properties is indistinguishable from human performance in a rapid scene categorization task in terms of both accuracy and false alarms. To what extent is this high predictability unique to a global property representation? In Experiment 4, we compared two models that represent scene object information to human categorization performance and found that these models had lower fidelity at representing the patterns of performance than the global property model. These results provide support for the hypothesis that rapid categorization of natural scenes may not be mediated primarily though objects and parts, but also through global properties of structure and affordance.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/597f80c9e5ee6c3439099e546232f8854afbea5c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Bayesian reconstruction of natural images from human brain activity (2009, unknown): “Although structural features underlying some categories of natural landscape (Greene and Oliva, 2009) have been discovered, the structural features underlying most semantic categories are still unknown (Griffin et al.”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “[13] Michelle R Greene, Aude Oliva, Recognition of natural scenes from global properties: Seeing the forest without representing the trees, Cognitive Psychology 58 (2) (2009) 137–176.”
The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding (2014, result): “This result supports the conclusions of Greene and Oliva (2009).”
Humans, but Not Deep Neural Networks, Often Miss Giant Targets in Scenes. (2017, background): “Factors [7] that guide visual search include bottom-up saliency, visual attributes (features) that deﬁne the target [26–30], properties of scenes that predict the likely target location [4, 6, 8, 13, 14, 19, 31–35], and rewards [36–39].”
Modeling Search for People in 900 Scenes: A combined source model of eye guidance (2009, unknown): “Within a glance, global information can provide useful information about spatial layout and scene category (Greene & Oliva, 2009; Joubert, Rousselet, Fize, & Fabre-Thorpe, 2007; McCotter, Gosselin, Sowden, & Schyns, 2005; Renninger & Malik, 2004; Rousselet, Joubert, & Fabre-Thorpe, 2005; Schyns &…”
A human-machine adversarial scoring framework for urban perception assessment using street-view images (2019, background): “Our visual system can recognize and classify scenes much faster than individual component objects, which usually take less about 100 ms in laboratory conditions (Greene and Oliva 2009b).”
SUN attribute database: Discovering, annotating, and recognizing scene attributes (2012, methodology): “This paper primarily focuses on the creation and verification of our SUN attribute database in the spirit of analogous database creation efforts such as ImageNet [3], LabelMe [19], and Tiny Images [22].”