this paper, we propose a Bayesian theory of hierarchical cortical computation based both on (a) the mathematical and computational ideas of computer vision and pattern the- ory and on (b) recent neurophysiological experimental evidence. We ,2 have proposed that Grenander's pattern theory 3 could potentially model the brain as a generafive model in such a way that feedback serves to disambiguate and 'explain away' the earlier representa- tion. The Helmholtz machine 4, 5 was an excellent step towards approximating this proposal, with feedback implementing priors. Its development, however, was rather limited, dealing only with binary images. Moreover, its feedback mechanisms were engaged only during the learning of the feedforward connections but not during perceptual inference, though the Gibbs sampling process for inference can potentially be interpreted as top-down feedback disambiguating low level representations? Rao and Ballard's predictive coding/Kalman filter model 6 did integrate generafive feedback in the perceptual inference process, but it was primarily a linear model and thus severely limited in practical utility. The data-driven Markov Chain Monte Carlo approach of Zhu and colleagues 7, 8 might be the most successful recent application of this proposal in solving real and difficult computer vision problems using generafive models, though its connection to the visual cortex has not been explored. Here, we bring in a powerful and widely applicable paradigm from artificial intelligence and computer vision to propose some new ideas about the algorithms of visual cortical process- ing and the nature of representations in the visual cortex. We will review some of our and others' neurophysiological experimental data to lend support to these ideas

Many experiments have shown that the human visual system makes extensive use of contextual information for facilitating object search in natural scenes. However, the question of how to formally model contextual influences is still open. On the basis of a Bayesian framework, the authors present an original approach of attentional guidance by global scene context. The model comprises 2 parallel pathways; one pathway computes local features (saliency) and the other computes global (scenecentered) features. The contextual guidance model of attention combines bottom-up saliency, scene context, and top-down mechanisms at an early stage of visual processing and predicts the image regions likely to be fixated by human observers performing natural search tasks in real-world scenes.

Abstract not found

We formulate a deformable template model for objects with a clearly defined mechanism for parameter estimation. A separate model is estimated for each class, and classification is likelihood based- no discrmination boundaries are learned. Nonethe-less high classification rates are achieved with small training samples. The data models are defined on binary oriented edge features that are highly robust to photometric vari-ation and small local deformations. The deformation of an object is defined in terms of locations of a moderate number reference points. Each reference point is associated with a part- a probability map assigning a probability for each edge type at each pixel in a window. The likelihood of the edge data on the entire image conditional on the deformation is described as a patchwork of parts (POP) model- the edges are assumed conditionally independent, and the marginal at each pixel is obtained by a patchwork operation: averaging the marginal probabilities contributed by each part covering the pixel. Object classes are modeled as mixtures of POP models that are discovered se-quentially as more class data is observed. Experiments are presented on the MNIST database, hundreds of deformed LATEX shapes, reading zipcodes, and face detection. 1

this article. We also thank Stephan Dekker for technical assistance

Abstract not found

This thesis describes an effort to construct a scene understanding system that is able to analyze the content of real images. While constructing the system we had to provide solutions to many of the fundamental questions that every student of object recognition deals with daily. These include the choice of data set, the choice of success measurement, the representation of the image content, the selection of inference engine, and the representation of the relations between objects. The main test-bed for our system is the CBCL StreetScenes data base. It is a carefully labeled set of images, much larger than any similar data set available at the time it was collected. Each image in this data set was labeled for 9 common classes such as cars, pedestrians, roads and trees. Our system represents each image using a set of features that are based on a model of the human visual system constructed in our lab. We demonstrate that this biologically motivated image representation, along with its extensions, constitutes an effective representation for object detection, facilitating unprecedented levels of detection

This article reports a theoretical and experimental attempt to relate and contrast 2 traditionally separate research programs: inattentional blindness and attention capture. Inattentional blindness refers to failures to notice unexpected objects and events when attention is otherwise engaged. Attention capture research has traditionally used implicit indices (e.g., response times) to investigate automatic shifts of attention. Because attention capture usually measures performance whereas inattentional blindness measures awareness, the 2 fields have existed side by side with no shared theoretical framework. Here, the authors propose a theoretical unification, adapting several important effects from the attention capture literature to the context of sustained inattentional blindness. Although some stimulus properties can influence noticing of unexpected objects, the most influential factor affecting noticing is a person’s own attentional goals. The authors conclude that many—but not all—aspects of attention capture apply to inattentional blindness but that these 2 classes of phenomena remain importantly distinct.

We advance a dominant neural strategy for facilitating conceptual thought. Concepts are groupings of “object ” attributes. Once the brain learns such critical groupings, the “object” attributes are inhibited from conscious awareness. We see the whole, not the parts. The details are inhibited when the concept network is activated, ie. the inhibition is dynamic and can be switched on and off. Autism is suggested to be the state of retarded concept formation. Our model predicts the possibility of accessing nonconscious information by artificially disinhibiting (turning off) the inhibiting networks associated with concept formation, using transcranial magnetic brain stimulation (TMS). For example, this opens the door for the restoration of perfect pitch, for recalling detail, for acquiring accent-free second languages beyond puberty, and even for enhancing creativity. The model further shows how unusual autistic savant skills as well as certain psychopathologies can be due respectively to privileged or inadvertent access to information that is normally inhibited from conscious awareness.

Studies have suggested attention-free semantic processing of natural scenes in which concurrent tasks