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

How long does it take for the human visual system to process a complex natural image? Subjectively, recognition of familiar objects and scenes appears to be virtually instantaneous, but measuring this processing time experimentally has proved difficult. Behavioural measures such as reaction times can be used, but these include not only visual processing but also the time required for response execution. However, event-related potentials (ERPs) can sometimes reveal signs of neural processing well before the motor output. Here we use a go/no-go categorization task in which subjects have to decide whether a previously unseen photograph, flashed on for just 20 ms, contains an animal. ERP analysis revealed a frontal negativity specific to no-go trials that develops roughly 150 ms after stimulus onset. We conclude that the visual processing needed to perform this highly demanding task can be achieved in under 150 ms.

Speed of processing in the human visual system.

Speed of processing in the human visual system

Single unit recording of neurons in the orbitofrontal cortex of the alert rhesus monkey was used to investigate responses to sensory stimulation. 32.4% of the neurons had visual responses that had typical latencies of 100–200 ms, and 9.4% responded to gustatory inputs. Most neurons were selective, in that they responded consistently to some stimuli such as foods or aversive objects, but not to others. In a number of cases the neurons responded selectively to particular foods or aversive stimuli. However, this high selectivity could not be explained by simple sensory features of the stimulus, since the responses of some neurons could be readily reversed if the meaning of the stimulus (i.e. whether it was food or aversive) was changed, even though its physical appearance remained identical. Further, some bimodal neurons received convergent visual and gustatory inputs, with matching selectivity for the same stimulus in both modalities, again suggesting that an explanation in terms of simple sensory features is inadequate.

The Orbitofrontal Cortex: Neuronal Activity in the Behaving Monkey

https://sccn.ucsd.edu/~arno/mypapers/ThorpeSpiking_Neurons.pdf

Spike-based strategies for rapid processing.

Experiments investigating the mechanisms involved in visual processing often fail to separate low-level encoding mechanisms from higher-level behaviorally relevant ones. Using an alternating dual-task event-related potential (ERP) experimental paradigm (animals or vehicles categorization) where targets of one task are intermixed among distractors of the other, we show that visual categorization of a natural scene involves different mechanisms with different time courses: a perceptual, task-independent mechanism, followed by a task-related, category-independent process. Although average ERP responses reflect the visual category of the stimulus shortly after visual processing has begun (e.g. 75–80 msec), this difference is not correlated with the subject's behavior until 150 msec poststimulus.

/pdf/the-time-course-of-visual-processing-from-early-perception-rk3msxhwwq.pdf

Simon J. Thorpe

Papers

Speed of processing in the human visual system.

Speed of processing in the human visual system

The Orbitofrontal Cortex: Neuronal Activity in the Behaving Monkey

Spike-based strategies for rapid processing.

The Time Course of Visual Processing: From Early Perception to Decision-Making