Blurred Images Lead to Bad Local Minima

High Initial visual Acuity (HIA) in newborns treated for cataracts, it is argued by Vogelsang et al. (2018), may cause impairments in configural face analysis. This HIA hypothesis is contrary to the standard explanation by a critical period for learning face processing. The hypothesis is supported by computational experiments with an artificial neural network. In our work we argue that the computational methodology used to evaluate the HIA hypothesis is flawed. It essentially shows that when a classifier is tested with images from different resolutions, the classifier benefits from seeing images from different resolution during its training. We therefore offer a better-fitting methodology; employing the modified methodology the HIA hypothesis does not hold in simulations using the same artificial neural network model, and the same data. Vogelsang et al. (2018) also show that initial exposure to low resolution images gives rise to larger receptive fields. Our last set of experiments tests the hypothesis that this might be the underlying reason for the observed impairments. Once again, we are unable to find an advantage to training with images of low initial acuity. We therefore conclude that simulations with artificial networks do not support the hypothesis that High Initial visual Acuity is detrimental.

[1]  Andrew Zisserman,et al.  Automated Flower Classification over a Large Number of Classes , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[2]  B. Röder,et al.  Sensitive periods for the functional specialization of the neural system for human face processing , 2013, Proceedings of the National Academy of Sciences.

[3]  Velma Dobson,et al.  Visual acuity in human infants: A review and comparison of behavioral and electrophysiological studies , 1978, Vision Research.

[4]  Nikolaus Kriegeskorte,et al.  Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation , 2014, PLoS Comput. Biol..

[5]  Stefan Winkler,et al.  A data-driven approach to cleaning large face datasets , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[6]  Nathan Witthoft,et al.  Reduced spatial integration in the ventral visual cortex underlies face recognition deficits in developmental prosopagnosia , 2016, bioRxiv.

[7]  Surya Ganguli,et al.  Biologically inspired protection of deep networks from adversarial attacks , 2017, ArXiv.

[8]  Ha Hong,et al.  Performance-optimized hierarchical models predict neural responses in higher visual cortex , 2014, Proceedings of the National Academy of Sciences.

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Albert Yonas,et al.  Potential downside of high initial visual acuity , 2018, Proceedings of the National Academy of Sciences.

[11]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[12]  Thomas Kindermann,et al.  Walknet--a biologically inspired network to control six-legged walking , 1998, Neural Networks.

[13]  Antonio Torralba,et al.  Recognizing indoor scenes , 2009, CVPR.