Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
COCO-Periph: Bridging the Gap Between Human and Machine Perception in the Periphery
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-932
Pre-trained DNN object detectors show a sharp falloff in peripheral detection performance with increasing eccentricity, degrading to near-chance by 20°, while human performance degrades gradually
IC-933
DNN object detectors do not exhibit the same sensitivity to image clutter as humans in peripheral object detection
IC-934
DNN object detectors do not exhibit the same object size effect as humans in peripheral object detection