Recurrent computations for visual pattern completion

by   Hanlin Tang, et al.

Making inferences from partial information constitutes a critical aspect of cognition. During visual perception, pattern completion enables recognition of poorly visible or occluded objects. We combined psychophysics, physiology and computational models to test the hypothesis that pattern completion is implemented by recurrent computations and present three pieces of evidence that are consistent with this hypothesis. First, subjects robustly recognized objects even when rendered <10 when processing was interrupted by backward masking. Second, invasive physiological responses along the human ventral cortex exhibited visually selective responses to partially visible objects that were delayed compared to whole objects, suggesting the need for additional computations. These physiological delays were correlated with the effects of backward masking. Third, state-of-the-art feed-forward computational architectures were not robust to partial visibility. However, recognition performance was recovered when the model was augmented with attractor-based recurrent connectivity. These results provide a strong argument of plausibility for the role of recurrent computations in making visual inferences from partial information.


page 6

page 34

page 36

page 37


Recurrent Feedback Improves Recognition of Partially Occluded Objects

Recurrent connectivity in the visual cortex is believed to aid object re...

Feed-forward approximations to dynamic recurrent network architectures

Recurrent neural network architectures can have useful computational pro...

Image Amodal Completion: A Survey

Existing computer vision systems can compete with humans in understandin...

Detection of Partially Visible Objects

An "elephant in the room" for most current object detection and localiza...

Recurrent circuits as multi-path ensembles for modeling responses of early visual cortical neurons

In this paper, we showed that adding within-layer recurrent connections ...

Please sign up or login with your details

Forgot password? Click here to reset