Simulating Visual Attention

Rapid visual categorization is not guided by early salience-based selection

The current dominant visual processing paradigm in both human and machine research is the feedforward, layered hierarchy of neural-like processing elements. Within this paradigm, visual saliency is seen by many to have a specific role, namely that of early selection. Early selection is thought to enable very fast visual performance by limiting processing to only the most salient candidate portions of an image. This strategy has led to a plethora of saliency algorithms that have indeed improved processing time efficiency in machine algorithms, which in turn have strengthened the suggestion that human vision also employs a similar early selection strategy. However, at least one set of critical tests of this idea has never been performed with respect to the role of early selection in human vision. How would the best of the current saliency models perform on the stimuli used by experimentalists who first provided evidence for this visual processing paradigm? Would the algorithms really provide correct candidate sub-images to enable fast categorization on those same images? Do humans really need this early selection for their impressive performance? Here, we report on a new series of tests of these questions whose results suggest that it is quite unlikely that such an early selection process has any role in human rapid visual categorization.

Towards the quantitative evaluation of visual attention models

Scores of visual attention models have been developed over the past several decades of research. Differences in implementation, assumptions, and evaluations have made comparison of these models very difficult. Taxonomies have been constructed in an attempt at the organization and classification of models, but are not sufficient at quantifying which classes of models are most capable of explaining available data. At the same time, a multitude of physiological and behavioral findings have been published, measuring various aspects of human and non-human primate visual attention. All of these elements highlight the need to integrate the computational models with the data by (1) operationalizing the definitions of visual attention tasks and (2) designing benchmark datasets to measure success on specific tasks, under these definitions. In this paper, we provide some examples of operationalizing and benchmarking different visual attention tasks, along with the relevant design considerations.

Using fuzzy logic to enhance stereo matching in multiresolution images

Stereo matching is an open problem in computer vision, for which local features are extracted to identify corresponding points in pairs of images. The results are heavily dependent on the initial steps. We apply image decomposition in multiresolution levels, for reducing the search space, computational time, and errors. We propose a solution to the problem of how deep (coarse) should the stereo measures start, trading between error minimization and time consumption, by starting stereo calculation at varying resolution levels, for each pixel, according to fuzzy decisions. Our heuristic enhances the overall execution time since it only employs deeper resolution levels when strictly necessary. It also reduces errors because it measures similarity between windows with enough details. We also compare our algorithm with a very fast multi-resolution approach, and one based on fuzzy logic. Our algorithm performs faster and/or better than all those approaches, becoming, thus, a good candidate for robotic vision applications. We also discuss the system architecture that efficiently implements our solution.

The effect of adapting luminance on the latency of visual search

Computational models of attentional processing typically view the "attentional spotlight" as a winner-take-all network whose focus can be shifted serially about a display if required. As a result, lateral inhibition is assumed in these models to be an important mechanism involved in visual search. On the basis of this assumption, we predicted that changes in adapting luminance would produce specific changes in search latency functions in virtue of affecting visual inhibition. The results of our first two experiments confirmed these predictions: when search was difficult, and produced reaction time results characteristic of serial processing, there was a main effect of adapting luminance and a significant interaction between adapting luminance and the number of display elements. These effects were both reflected in increases in the slopes and the intercepts of average search latency functions when adapting luminance was decreased. When search was easy, and produced pop out effects characteristic of parallel processing, there were no significant effects of adapting luminance on search latency. The third experiment used adapting luminance to further explore the possibility that arrow junctions are detected preattentively. The results suggested that a visual search for such elements involves a substantial serial component, which weighs against the claim that they are detected by low-level vision.

Computational approaches to cognition: the bottom-up view

How can higher level aspects of cognition, such as figure-ground segregation, object recognition, selective focal attention and ultimately even awareness, be implemented at the level of synapses and neurons? A number of theoretical studies emerging out of the connectionist and the computational neuroscience communities are starting to address these issues using neural plausible models.