2017/06/07 by Joshua C. Peterson, Peterson, Joshua C., Joshua T. Abbott +3
Computer Science · Neuroscience · Psychology · #Child and Animal Learning Development #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Face Recognition and Perception #cs.CV
paper · pdf · doi:10.48550/arxiv.1706.02417
35 pages, 8 figures, accepted for publication in Cognitive Science
openalex publication_date 2017/06/07 · arxiv created 2018/07/24 · arxiv updated 2018/07/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Decades of psychological research have been aimed at modeling how people learn features and categories. The empirical validation of these theories is often based on artificial stimuli with simple representations. Recently, deep neural networks have reached or surpassed human accuracy on tasks such as identifying objects in natural images. These networks learn representations of real-world stimuli that can potentially be leveraged to capture psychological representations. We find that state-of-the-art object classification networks provide surprisingly accurate predictions of human similarity judgments for natural images, but fail to capture some of the structure represented by people. We show that a simple transformation that corrects these discrepancies can be obtained through convex optimization. We use the resulting representations to predict the difficulty of learning novel categories of natural images. Our results extend the scope of psychological experiments and computational modeling by enabling tractable use of large natural stimulus sets.