Ultra-fast image categorization in vivo and in silico

  title={Ultra-fast image categorization in vivo and in silico},
  author={Jean-Nicolas J'er'emie and Laurent Udo Perrinet},
— Humans are able to robustly categorize images and can, for instance, detect the presence of an animal in a briefly flashed image in as little as 120 ms . Initially inspired by neuroscience, deep-learning algorithms literally bloomed up in the last decade such that the accuracy of machines is at present superior to humans for visual recognition tasks. However, these artificial networks are usually trained and evaluated on very specific tasks, for instance on the 1000 separate categories of I MAGE… 

Precise Spiking Motifs in Neurobiological and Neuromorphic Data

This review paper provides evidence from biology, theory and engineering that the precise timing of spikes plays a crucial role in the understanding of the efficiency of neural networks.



How transferable are features in deep neural networks?

This paper quantifies the generality versus specificity of neurons in each layer of a deep convolutional neural network and reports a few surprising results, including that initializing a network with transferred features from almost any number of layers can produce a boost to generalization that lingers even after fine-tuning to the target dataset.

Animal Detection in Natural Images: Effects of Color and Image Database

The ANID image database is better suited for the investigation of the processing of natural scenes than other databases commonly used, and is concluded that ultra-fast processing of animal images is possible irrespective of the particular database.

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

Convolutional neural networks trained with a developmental sequence of blurry to clear images reveal core differences between face and object processing

The results suggest that blurry vision during infancy is insufficient to account for the robustness of adult vision to blurry objects, providing novel computational evidence showing how face recognition, unlike object recognition, allows for more holistic processing.

The Time-Course of Visual Categorizations: You Spot the Animal Faster than the Bird

This work compared human processing speed when categorizing natural scenes as containing either an animal (superordinate level), or a specific animal (bird or dog, basic level) and found the basic level category is accessed as fast as the superordinate category.

Edge co-occurrences can account for rapid categorization of natural versus animal images

The statistics of edge co-occurrences alone are sufficient to perform a rough yet robust (translation, scale, and rotation invariant) scene categorization and suggest new algorithms for image classification and signal processing that exploit correlations between low-level structure and the underlying semantic category.

Key Visual Features for Rapid Categorization of Animals in Natural Scenes

The results support fast diagnostic recognition of animals based on key intermediate features and priming based on the subject's expertise as well as agreement with other experimental and modeling studies.

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence

It was shown that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams and provided an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain.

The Pascal Visual Object Classes Challenge: A Retrospective

A review of the Pascal Visual Object Classes challenge from 2008-2012 and an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.