Deep Learning: The Good, the Bad, and the Ugly.

Artificial vision has often been described as one of the key remaining challenges to be solved before machines can act intelligently. Recent developments in a branch of machine learning known as deep learning have catalyzed impressive gains in machine vision-giving a sense that the problem of vision is getting closer to being solved. The goal of this review is to provide a comprehensive overview of recent deep learning developments and to critically assess actual progress toward achieving human-level visual intelligence. I discuss the implications of the successes and limitations of modern machine vision algorithms for biological vision and the prospect for neuroscience to inform the design of future artificial vision systems. Expected final online publication date for the Annual Review of Vision Science, Volume 5 is September 16, 2019. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

[1]  Alexei A. Efros,et al.  Colorful Image Colorization , 2016, ECCV.

[2]  Yoshua Bengio,et al.  Equilibrium Propagation: Bridging the Gap between Energy-Based Models and Backpropagation , 2016, Front. Comput. Neurosci..

[3]  Swami Sankaranarayanan,et al.  Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms , 2018, Proceedings of the National Academy of Sciences.

[4]  Jun Zhu,et al.  Visual Concepts and Compositional Voting , 2017, ArXiv.

[5]  Thomas L. Griffiths,et al.  Evaluating (and Improving) the Correspondence Between Deep Neural Networks and Human Representations , 2017, Cogn. Sci..

[6]  David Cox,et al.  Recurrent computations for visual pattern completion , 2017, Proceedings of the National Academy of Sciences.

[7]  Mike Preuss,et al.  Planning chemical syntheses with deep neural networks and symbolic AI , 2017, Nature.

[8]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Justus H. Piater,et al.  25 Years of CNNs: Can We Compare to Human Abstraction Capabilities? , 2016, ICANN.

[10]  Chaz Firestone,et al.  Humans can decipher adversarial images , 2018, Nature Communications.

[11]  Rafal Bogacz,et al.  An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity , 2017, Neural Computation.

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

[13]  Razvan Pascanu,et al.  A simple neural network module for relational reasoning , 2017, NIPS.

[14]  Eero P. Simoncelli,et al.  A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients , 2000, International Journal of Computer Vision.

[15]  Michael Wainberg,et al.  Deep learning in biomedicine , 2018, Nature Biotechnology.

[16]  Demis Hassabis,et al.  A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play , 2018, Science.

[17]  Kazuhiro Terao,et al.  Machine learning at the energy and intensity frontiers of particle physics , 2018, Nature.

[18]  Thomas Serre,et al.  Hierarchical Models of the Visual System , 2014, Encyclopedia of Computational Neuroscience.

[19]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[20]  Shimon Ullman,et al.  Atoms of recognition in human and computer vision , 2016, Proceedings of the National Academy of Sciences.

[21]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[22]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[23]  Bolei Zhou,et al.  Interpreting Deep Visual Representations via Network Dissection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Nikolaus Kriegeskorte,et al.  Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition , 2017, bioRxiv.

[25]  Carlos R. Ponce,et al.  Evolving Images for Visual Neurons Using a Deep Generative Network Reveals Coding Principles and Neuronal Preferences , 2019, Cell.

[26]  Pascal Frossard,et al.  Dictionary Learning , 2011, IEEE Signal Processing Magazine.

[27]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[28]  Lujo Bauer,et al.  A General Framework for Adversarial Examples with Objectives , 2017, ACM Trans. Priv. Secur..

[29]  Andrew Zisserman,et al.  Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.

[30]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[31]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[32]  J. DiCarlo,et al.  Using goal-driven deep learning models to understand sensory cortex , 2016, Nature Neuroscience.

[33]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[34]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[35]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.