Deeper neural network models better reflect how humans cope with contrast variation in object recognition.

Journal: Neuroscience research
PMID:

Abstract

Visual inputs are far from ideal in everyday situations such as in the fog where the contrasts of input stimuli are low. However, human perception remains relatively robust to contrast variations. To provide insights about the underlying mechanisms of contrast invariance, we addressed two questions. Do contrast effects disappear along the visual hierarchy? Do later stages of the visual hierarchy contribute to contrast invariance? We ran a behavioral experiment where we manipulated the level of stimulus contrast and the involvement of higher-level visual areas through immediate and delayed backward masking of the stimulus. Backward masking led to significant drop in performance in our visual categorization task, supporting the role of higher-level visual areas in contrast invariance. To obtain mechanistic insights, we ran the same categorization task on three state-of the-art computational models of human vision each with a different depth in visual hierarchy. We found contrast effects all along the visual hierarchy, no matter how far into the hierarchy. Moreover, that final layers of deeper hierarchical models, which had been shown to be best models of final stages of the visual system, coped with contrast effects more effectively. These results suggest that, while contrast effects reach the final stages of the hierarchy, those stages play a significant role in compensating for contrast variations in the visual system.

Authors

  • Masoumeh Mokari-Mahallati
    Department of Electrical Engineering, Shahid Rajaee Teacher Training University, Tehran, Islamic Republic of Iran.
  • Reza Ebrahimpour
    Institute for Convergence Science and Technology (ICST), Sharif University of Technology, Tehran, Iran; Faculty of Computer Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran; School of Cognitive Sciences (SCS), Institute for Research in Fundamental Sciences (IPM), Tehran, Iran.
  • Nasour Bagheri
    Department of Electrical Engineering, Shahid Rajaee Teacher Training University, Tehran, Islamic Republic of Iran.
  • Hamid Karimi-Rouzbahani
    MRC Cognition & Brain Sciences Unit, University of Cambridge, UK; Mater Research Institute, Faculty of Medicine, University of Queensland, Australia.