Ernst Niebur

Bio: Ernst Niebur is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Visual cortex & Receptive field. The author has an hindex of 37, co-authored 144 publications receiving 17021 citations. Previous affiliations of Ernst Niebur include University of Lausanne & Allen Institute for Brain Science.

A model of saliency-based visual attention for rapid scene analysis

Abstract: A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail.

Attention modulates synchronized neuronal firing in primate somatosensory cortex.

Abstract: A potentially powerful information processing strategy in the brain is to take advantage of the temporal structure of neuronal spike trains. An increase in synchrony within the neural representation of an object or location increases the efficacy of that neural representation at the next synaptic stage in the brain; thus, increasing synchrony is a candidate for the neural correlate of attentional selection. We investigated the synchronous firing of pairs of neurons in the secondary somatosensory cortex (SII) of three monkeys trained to switch attention between a visual task and a tactile discrimination task. We found that most neuron pairs in SII cortex fired synchronously and, furthermore, that the degree of synchrony was affected by the monkey's attentional state. In the monkey performing the most difficult task, 35% of neuron pairs that fired synchronously changed their degree of synchrony when the monkey switched attention between the tactile and visual tasks. Synchrony increased in 80% and decreased in 20% of neuron pairs affected by attention.

Neural Correlates of High-Gamma Oscillations (60–200 Hz) in Macaque Local Field Potentials and Their Potential Implications in Electrocorticography

Abstract: Recent studies using electrocorticographic (ECoG) recordings in humans have shown that functional activation of cortex is associated with an increase in power in the high-gamma frequency range (∼60–200 Hz). Here we investigate the neural correlates of this high-gamma activity in local field potential (LFP). Single units and LFP were recorded with microelectrodes from the hand region of macaque secondary somatosensory cortex while vibrotactile stimuli of varying intensities were presented to the hand. We found that high-gamma power in the LFP was strongly correlated with the average firing rate recorded by the microelectrodes, both temporally and on a trial-by-trial basis. In comparison, the correlation between firing rate and low-gamma power (40–80 Hz) was much smaller. To explore the potential effects of neuronal firing on ECoG, we developed a model to estimate ECoG power generated by different firing patterns of the underlying cortical population and studied how ECoG power varies with changes in firing rate versus the degree of synchronous firing between neurons in the population. Both an increase in firing rate and neuronal synchrony increased high-gamma power in the simulated ECoG data. However, ECoG high-gamma activity was much more sensitive to increases in neuronal synchrony than firing rate.

Scene content selected by active vision.

Abstract: The primate visual system actively selects visual information from the environment for detailed processing through mechanisms of visual attention and saccadic eye movements. This study examines the statistical properties of the scene content selected by active vision. Eye movements were recorded while participants free-viewed digitized images of natural and artificial scenes. Fixation locations were determined for each image and image patches were extracted around the observed fixation locations. Measures of local contrast, local spatial correlation and spatial frequency content were calculated on the extracted image patches. Replicating previous results, local contrast was found to be greater at the points of fixation when compared to either the contrast for image patches extracted at random locations or at the observed fixation locations using an image-shuffled database. Contrary to some results and in agreement with other results in the literature, a significant decorrelation of image intensity is observed between the locations of fixation and other neighboring locations. A discussion and analysis of methodological techniques is given that provides an explanation for the discrepancy in results. The results of our analyses indicate that both the local contrast and correlation at the points of fixation are a function of image type and, furthermore, that the magnitude of these effects depend on the levels of contrast and correlation present overall in the images. Finally, the largest effect sizes in local contrast and correlation are found at distances of approximately 1 deg of visual angle, which agrees well with measures of optimal spatial scale selectivity in the visual periphery where visual information for potential saccade targets is processed.

Rapid object detection using a boosted cascade of simple features

Abstract: This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.

Squeeze-and-Excitation Networks

Abstract: The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of ${\sim }$ ∼ 25 percent. Models and code are available at https://github.com/hujie-frank/SENet .

Robust Real-Time Face Detection

Abstract: This paper describes a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is the introduction of a new image representation called the “Integral Image” which allows the features used by our detector to be computed very quickly. The second is a simple and efficient classifier which is built using the AdaBoost learning algorithm (Freund and Schapire, 1995) to select a small number of critical visual features from a very large set of potential features. The third contribution is a method for combining classifiers in a “cascade” which allows background regions of the image to be quickly discarded while spending more computation on promising face-like regions. A set of experiments in the domain of face detection is presented. The system yields face detection performance comparable to the best previous systems (Sung and Poggio, 1998; Rowley et al., 1998; Schneiderman and Kanade, 2000; Roth et al., 2000). Implemented on a conventional desktop, face detection proceeds at 15 frames per second.

Robust real-time face detection

Abstract: This paper describes a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is the introduction of a new image representation called the "Integral Image" which allows the features used by our detector to be computed very quickly. The second is a simple and efficient classifier which is built using the AdaBoost learning algo- rithm (Freund and Schapire, 1995) to select a small number of critical visual features from a very large set of potential features. The third contribution is a method for combining classifiers in a "cascade" which allows back- ground regions of the image to be quickly discarded while spending more computation on promising face-like regions. A set of experiments in the domain of face detection is presented. The system yields face detection perfor- mance comparable to the best previous systems (Sung and Poggio, 1998; Rowley et al., 1998; Schneiderman and Kanade, 2000; Roth et al., 2000). Implemented on a conventional desktop, face detection proceeds at 15 frames per second.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.