The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.

/pdf/imagenet-large-scale-visual-recognition-challenge-caky5nmmix.pdf

ImageNet Large Scale Visual Recognition Challenge

Prelude. Cycle 1. Introduction. Cycle 2. Structure defines function. Cycle 3. Diversity of cortical functions is provided by inhibition. Cycle 4. Windows on the brain. Cycle 5. A system of rhythms: from simple to complex dynamics. Cycle 6. Synchronization by oscillation. Cycle 7. The brain's default state: self-organized oscillations in rest and sleep. Cycle 8. Perturbation of the default patterns by experience. Cycle 9. The gamma buzz: gluing by oscillations in the waking brain. Cycle 10. Perceptions and actions are brain state-dependent. Cycle 11. Oscillations in the "other cortex:" navigation in real and memory space. Cycle 12. Coupling of systems by oscillations. Cycle 13. The tough problem. References.

Rhythms of the brain

Schultz, Wolfram. Predictive reward signal of dopamine neurons. J. Neurophysiol. 80: 1–27, 1998. The effects of lesions, receptor blocking, electrical self-stimulation, and drugs of abuse suggest t...

/pdf/predictive-reward-signal-of-dopamine-neurons-3f94myirza.pdf

Predictive Reward Signal of Dopamine Neurons

We propose a novel approach to learn and recognize natural scene categories. Unlike previous work, it does not require experts to annotate the training set. We represent the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning. Each region is represented as part of a "theme". In previous work, such themes were learnt from hand-annotations of experts, while our method learns the theme distributions as well as the codewords distribution over the themes without supervision. We report satisfactory categorization performances on a large set of 13 categories of complex scenes.

/pdf/a-bayesian-hierarchical-model-for-learning-natural-scene-zzqtm1es9k.pdf

A Bayesian hierarchical model for learning natural scene categories

Visual processing in cortex is classically modeled as a hierarchy of increasingly sophisticated representations, naturally extending the model of simple to complex cells of Hubel and Wiesel. Surprisingly, little quantitative modeling has been done to explore the biological feasibility of this class of models to explain aspects of higher-level visual processing such as object recognition. We describe a new hierarchical model consistent with physiological data from inferotemporal cortex that accounts for this complex visual task and makes testable predictions. The model is based on a MAX-like operation applied to inputs to certain cortical neurons that may have a general role in cortical function.

/pdf/hierarchical-models-of-object-recognition-in-cortex-33mmp5yhnv.pdf

Hierarchical models of object recognition in cortex

http://audition.ens.fr/dp/pdfs/AgusThorpePressnitzer-2010-noise_memory.pdf

Rapid Formation of Robust Auditory Memories: Insights from Noise

Accurate binocular depth perception requires information about both stereopsis (relative depth) and distance (absolute depth). It is unclear how these two types of information are integrated in the visual system. In alert, behaving monkeys the responsiveness of a large majority of neurons in the primary visual cortex (area V1) was modulated by the viewing distance. This phenomenon affected particularly disparity-related activity and background activity and was not dependent on the pattern of retinal stimulation. Therefore, extraretinal factors, probably related to ocular vergence or accommodation, or both, can affect processing early in the visual pathway. Such modulations could be useful for (i) judging true distance and (ii) scaling retinal disparity to give information about three-dimensional shape.

http://science.sciencemag.org/content/sci/257/5074/1279.full.pdf

Modulation of neural stereoscopic processing in primate area V1 by the viewing distance.

Energy absorbing crash or collision devices for vehicles or the like to reduce shock of collision by utilizing energy absorbing components which are flexible and compressible and/or rigid and crushable, which components may used singly or in combination, which may be used with single or multiple pressure plates, to effect gradual deceleration upon collision.

Spike arrival times: A highly efficient coding scheme for neural networks

Spike timing-dependent plasticity (STDP) is a learning rule that modifies the strength of a neuron's synapses as a function of the precise temporal relations between input and output spikes. In many brains areas, temporal aspects of spike trains have been found to be highly reproducible. How will STDP affect a neuron's behavior when it is repeatedly presented with the same input spike pattern? We show in this theoretical study that repeated inputs systematically lead to a shaping of the neuron's selectivity, emphasizing its very first input spikes, while steadily decreasing the postsynaptic response latency. This was obtained under various conditions of background noise, and even under conditions where spiking latencies and firing rates, or synchrony, provided conflicting informations. The key role of first spikes demonstrated here provides further support for models using a single wave of spikes to implement rapid neural processing.

Simon J. Thorpe

Papers

Rapid Formation of Robust Auditory Memories: Insights from Noise

Modulation of neural stereoscopic processing in primate area V1 by the viewing distance.

Spike arrival times: A highly efficient coding scheme for neural networks

Neurons Tune to the Earliest Spikes Through STDP

2012 Special Issue: Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity