AIMC Topic: Visual Perception

Clear Filters Showing 111 to 120 of 377 articles

Extreme image transformations affect humans and machines differently.

Biological cybernetics
Some recent artificial neural networks (ANNs) claim to model aspects of primate neural and human performance data. Their success in object recognition is, however, dependent on exploiting low-level features for solving visual tasks in a way that huma...

Recognizing Object by Components With Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks.

IEEE transactions on pattern analysis and machine intelligence
Adversarial attacks can easily fool object recognition systems based on deep neural networks (DNNs). Although many defense methods have been proposed in recent years, most of them can still be adaptively evaded. One reason for the weak adversarial ro...

Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRI.

IEEE transactions on medical imaging
The long acquisition time has limited the accessibility of magnetic resonance imaging (MRI) because it leads to patient discomfort and motion artifacts. Although several MRI techniques have been proposed to reduce the acquisition time, compressed sen...

JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments.

IEEE transactions on pattern analysis and machine intelligence
We present JRDB, a novel egocentric dataset collected from our social mobile manipulator JackRabbot. The dataset includes 64 minutes of annotated multimodal sensor data including stereo cylindrical 360 RGB video at 15 fps, 3D point clouds from two 1...

Quantum spin models for numerosity perception.

PloS one
Humans share with animals, both vertebrates and invertebrates, the capacity to sense the number of items in their environment already at birth. The pervasiveness of this skill across the animal kingdom suggests that it should emerge in very simple po...

Multifunctional Optoelectronic Synapses Based on Arrayed MoS Monolayers Emulating Human Association Memory.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)
Optoelectronic synaptic devices integrating light-perception and signal-storage functions hold great potential in neuromorphic computing for visual information processing, as well as complex brain-like learning, memorizing, and reasoning. Herein, the...

Are Deep Neural Networks Adequate Behavioral Models of Human Visual Perception?

Annual review of vision science
Deep neural networks (DNNs) are machine learning algorithms that have revolutionized computer vision due to their remarkable successes in tasks like object classification and segmentation. The success of DNNs as computer vision algorithms has led to ...

Robust deep learning object recognition models rely on low frequency information in natural images.

PLoS computational biology
Machine learning models have difficulty generalizing to data outside of the distribution they were trained on. In particular, vision models are usually vulnerable to adversarial attacks or common corruptions, to which the human visual system is robus...

EXPLORE: a novel deep learning-based analysis method for exploration behaviour in object recognition tests.

Scientific reports
Object recognition tests are widely used in neuroscience to assess memory function in rodents. Despite the experimental simplicity of the task, the interpretation of behavioural features that are counted as object exploration can be complicated. Thus...

Mammalian-brain-inspired neuromorphic motion-cognition nerve achieves cross-modal perceptual enhancement.

Nature communications
Perceptual enhancement of neural and behavioral response due to combinations of multisensory stimuli are found in many animal species across different sensory modalities. By mimicking the multisensory integration of ocular-vestibular cues for enhance...