AIMC Topic: Pattern Recognition, Visual

Clear Filters Showing 71 to 80 of 145 articles

A fully convolutional two-stream fusion network for interactive image segmentation.

Neural networks : the official journal of the International Neural Network Society
In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactiveimage segmentation. The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a red...

Dense Associative Memory Is Robust to Adversarial Inputs.

Neural computation
Deep neural networks (DNNs) trained in a supervised way suffer from two known problems. First, the minima of the objective function used in learning correspond to data points (also known as rubbish examples or fooling images) that lack semantic simil...

Creatures great and small: Real-world size of animals predicts visual cortex representations beyond taxonomic category.

NeuroImage
Human occipitotemporal cortex contains neural representations for a variety of perceptual and conceptual features. We report a study examining neural representations of real-world size along the visual ventral stream, while carefully accounting for t...

Image categorization from functional magnetic resonance imaging using functional connectivity.

Journal of neuroscience methods
BACKGROUND: Previous studies have attempted to infer the category of objects in a stimulus image from functional magnetic resonance imaging (fMRI) data recoded during image-viewing. Most studies focus on extracting activity patterns within a given re...

Adaptive non-negative projective semi-supervised learning for inductive classification.

Neural networks : the official journal of the International Neural Network Society
We discuss the inductive classification problem by proposing a joint framework termed Adaptive Non-negative Projective Semi-Supervised Learning (ANP-SSL). Specifically, ANP-SSL integrates the adaptive inductive label propagation, adaptive reconstruct...

Generative adversarial networks for reconstructing natural images from brain activity.

NeuroImage
We explore a method for reconstructing visual stimuli from brain activity. Using large databases of natural images we trained a deep convolutional generative adversarial network capable of generating gray scale photos, similar to stimuli presented du...

Neuro-cognitive mechanisms of global Gestalt perception in visual quantification.

NeuroImage
Recent neuroimaging studies identified posterior regions in the temporal and parietal lobes as neuro-functional correlates of subitizing and global Gestalt perception. Beyond notable overlap on a neuronal level both mechanisms are remarkably similar ...

Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks.

The Journal of neuroscience : the official journal of the Society for Neuroscience
Primates, including humans, can typically recognize objects in visual images at a glance despite naturally occurring identity-preserving image transformations (e.g., changes in viewpoint). A primary neuroscience goal is to uncover neuron-level mechan...

Reproducibility of importance extraction methods in neural network based fMRI classification.

NeuroImage
Recent advances in machine learning allow faster training, improved performance and increased interpretability of classification techniques. Consequently, their application in neuroscience is rapidly increasing. While classification approaches have p...

Prospective motion correction improves the sensitivity of fMRI pattern decoding.

Human brain mapping
We evaluated the effectiveness of prospective motion correction (PMC) on a simple visual task when no deliberate subject motion was present. The PMC system utilizes an in-bore optical camera to track an external marker attached to the participant via...