2017/01/10 by Drew Linsley, Sven Eberhardt, Linsley, Drew +7
Computer Science · Neuroscience · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Face Recognition and Perception #Visual Attention and Saliency Detection #Visual perception and processing mechanisms
paper · pdf · doi:10.48550/arxiv.1701.02704
openalex publication_date 2017/01/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Although Deep Convolutional Networks (DCNs) are approaching the accuracy of human observers at object recognition, it is unknown whether they leverage similar visual representations to achieve this performance. To address this, we introduce Clicktionary, a web-based game for identifying visual features used by human observers during object recognition. Importance maps derived from the game are consistent across participants and uncorrelated with image saliency measures. These results suggest that Clicktionary identifies image regions that are meaningful and diagnostic for object recognition but different than those driving eye movements. Surprisingly, Clicktionary importance maps are only weakly correlated with relevance maps derived from DCNs trained for object recognition. Our study demonstrates that the narrowing gap between the object recognition accuracy of human observers and DCNs obscures distinct visual strategies used by each to achieve this performance.