The main challenge of few-shot learning lies in the limited labeled sample data. In addition, since image-level labels are usually not accurate describing features images, it leads to difficulty for model have good generalization ability and robustness. This problem has been well solved yet, existing metric-based methods still room improvement. To address this issue, we propose a method based o...

In the Simon task, participants respond faster when the task-irrelevant stimulus position and the response position are corresponding, for example on the same side, compared to when they have a non-corresponding relation. Interestingly, this Simon effect is reduced after non-corresponding trials. Such sequential effects can be explained in terms of a more focused processing of the relevant stim...

This article examines the relation between changing categorization decision rules and the nature of the underlying perceptual representation. Observers completed a matching task that required them to adjust the length and orientation of a single line stimulus until they perceived it to "match" a second line stimulus (Alfonso-Reese, 1996, 1997). The same observers then completed four categorizat...

In the outside world, response selection often requires the processing of information from different spatial dimensions. Yet, most neuroscientific approaches to the topic only employ variations in one dimension, namely the horizontal left-right axis. Hence, virtually nothing is known about the neuronal mechanisms underlying response selection in more than one dimension. We investigated this asp...

Electrophysiological measurements were taken from observers performing a visual search within a single feature dimension, and between multiple dimensions. The N2pc to selected singleton target stimuli (rightward tilted lines) was increased when targets varied between feature dimensions, compared to the N2pc to the same rightward tilted line targets, in a condition in which targets varied only b...

We assess the performance of hybrid Open Accelerator (OpenACC) and Message Passing Interface (MPI) approach for multi-graphics processing units (GPUs) accelerated thermal lattice Boltzmann (LB) simulation. The OpenACC accelerates computation on a single GPU, MPI synchronizes information between multiple GPUs. With two-dimension (2D) simulation achieved 1.93 billion updates per second (GLUPS) wi...