Related papers: Learning to combine top-down context and feed-forw…

In the fields of brain-computer interaction and cognitive neuroscience, effective decoding of auditory signals from task-based functional magnetic resonance imaging (fMRI) is key to understanding how the brain processes complex auditory…

Classifying the sub-categories of an object from the same super-category (e.g. bird species, car and aircraft models) in fine-grained visual classification (FGVC) highly relies on discriminative feature representation and accurate region…

A central challenge in neuroscience is to understand neural computations and circuit mechanisms that underlie the encoding of ethologically relevant, natural stimuli. In multilayered neural circuits, nonlinear processes such as synaptic…

Data driven segmentation is an important initial step of shape prior-based segmentation methods since it is assumed that the data term brings a curve to a plausible level so that shape and data terms can then work together to produce better…

Superpixel segmentation has seen significant progress benefiting from the deep convolutional networks. The typical approach entails initial division of the image into grids, followed by a learning process that assigns each pixel to adjacent…

Context modeling is one of the most fertile subfields of visual recognition which aims at designing discriminant image representations while incorporating their intrinsic and extrinsic relationships. However, the potential of context…

Humans and animals have a rich and flexible understanding of the physical world, which enables them to infer the underlying dynamical trajectories of objects and events, plausible future states, and use that to plan and anticipate the…

Current deep learning methods for object recognition are purely data-driven and require a large number of training samples to achieve good results. Due to their sole dependence on image data, these methods tend to fail when confronted with…

Deep learning techniques have demonstrated significant capacity in modeling some of the most challenging real world problems of high complexity. Despite the popularity of deep models, we still strive to better understand the underlying…

We introduce a method for training neural networks to perform image or volume segmentation in which prior knowledge about the topology of the segmented object can be explicitly provided and then incorporated into the training process. By…

Semantic segmentation is challenging as it requires both object-level information and pixel-level accuracy. Recently, FCN-based systems gained great improvement in this area. Unlike classification networks, combining features of different…

Recent conditional image generation methods can improve controllability by generating images that are faithful to conditions such as sketches, human poses, segmentation maps, and depth. By applying these techniques to image augmentation…

Visual priming is known to affect the human visual system to allow detection of scene elements, even those that may have been near unnoticeable before, such as the presence of camouflaged animals. This process has been shown to be an effect…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Neural networks encode inputs as high-dimensional vectors, known as representations, that capture how models process data by encoding task-relevant structure and semantics. Representation alignment refers to the degree to which different…

Traditional neuron models use analog values for information representation and computation, while all-or-nothing spikes are employed in the spiking ones. With a more brain-like processing paradigm, spiking neurons are more promising for…

The brain's spatial orientation system uses different neuron ensembles to aid in environment-based navigation. Two of the ways brains encode spatial information is through head direction cells and grid cells. Brains use head direction cells…

Recognition of every word is accomplished by close collaboration of bottom-up sub-word and word recognition neural networks with top-down cognitive word context expectations. The utility of this context appropriate collaboration is…

Traditional analytical reflectance models, while compact and interpretable, lack the capacity to accurately represent physical measurements. Recent neural models, which closely fit input data, are less generalizable and often more expensive…

The increasing need for intelligent sensors in a wide range of everyday objects requires the existence of low power information processing systems which can operate autonomously in their environment. In particular, merging and processing…