Search

Non-accidental properties (NAPs) correspond to image properties that are invariant to changes in viewpoint (e.g., straight vs. curved contours) and are distinguished from metric properties (MPs) that can change continuously with in-depth object rotation (e.g., aspect ratio, degree of curvature, etc). Behavioral and electrophysiological studies of shape processing have demonstrated greater sensitivity to differences in NAPs than in MPs. However, previous work has shown that such sensitivity is lacking in multiple-views models of object recognition such as textsc{Hmax}. These models typically assume that object processing is based on populations of view-tuned neurons with distributed symmetrical bell-shaped tuning that are modulated at least as much by differences in MPs as in NAPs.Here, we test the hypothesis that unsupervised learning of invariances to object transformations may increase the sensitivity to differences in NAPs vs. MPs in textsc{Hmax}. We collected a database of video sequences with objects slowly rotating in-depth in an attempt to mimic sequences viewed during object manipulation by young children during early developmental stages. We show that unsupervised learning yields shape-tuning in higher stages with greater sensitivity to differences in NAPs vs. MPs in agreement with monkey IT data. Together, these results suggest that greater NAP sensitivity may arise from experiencing different in-depth rotations of objects.

Searching for and recognising objects in complex natural scenes is implemented by multiple saccades until the eyes reach within the reduced receptive field sizes of inferior temporal cortex (IT) neurons. We analyse and model how the dorsal and ventral visual streams both contribute to this. Saliency detection in the dorsal visual system including area LIP is modelled by graph-based visual saliency, and allows the eyes to fixate potential objects within several degrees. Visual information at the fixated location subtending approximately 9 degrees corresponding to the receptive fields of IT neurons is then passed through a four layer hierarchical model of the ventral cortical visual system, VisNet. We show that VisNet can be trained using a synaptic modification rule with a short-term memory trace of recent neuronal activity to capture both the required view and translation invariances to allow in the model approximately 90% correct object recognition for 4 objects shown in any view across a range of 135 degrees anywhere in a scene.The model was able to generalize correctly within the four trained views and the 25 trained translations.This approach analyses the principles by which complementary computations in the dorsal and ventral visual cortical streams enable objects to be located and recognised in complex natural scenes.

Non-accidental properties (NAPs) correspond to image properties that are invariant to changes in viewpoint (e.g., straight vs. curved contours) and are distinguished from metric properties (MPs) that can change continuously with in-depth object rotation (e.g., aspect ratio, degree of curvature, etc.). Behavioral and electrophysiological studies of shape processing have demonstrated greater sensitivity to differences in NAPs than in MPs. However, previous work has shown that such sensitivity is lacking in multiple-views models of object recognition such as HMAX. These models typically assume that object processing is based on populations of view-tuned neurons with distributed symmetrical bell-shaped tuning that are modulated at least as much by differences in MPs as in NAPs. Here, we test the hypothesis that unsupervised learning of invariances to object transformations may increase the sensitivity to differences in NAPs vs. MPs in HMAX. We collected a database of video sequences with objects slowly rotating in-depth in an attempt to mimic sequences viewed during object manipulation by young children during early developmental stages. We show that unsupervised learning yields shape-tuning in higher stages with greater sensitivity to differences in NAPs vs. MPs in agreement with monkey IT data. Together, these results suggest that greater NAP sensitivity may arise from experiencing different in-depth rotations of objects. [ABSTRACT FROM AUTHOR]

Searching for and recognizing objects in complex natural scenes is implemented by multiple saccades until the eyes reach within the reduced receptive field sizes of inferior temporal cortex (IT) neurons. We analyze and model how the dorsal and ventral visual streams both contribute to this. Saliency detection in the dorsal visual system including area LIP is modeled by graph-based visual saliency, and allows the eyes to fixate potential objects within several degrees. Visual information at the fixated location subtending approximately 9° corresponding to the receptive fields of IT neurons is then passed through a four layer hierarchical model of the ventral cortical visual system, VisNet. We show that VisNet can be trained using a synaptic modification rule with a short-term memory trace of recent neuronal activity to capture both the required view and translation invariances to allow in the model approximately 90% correct object recognition for 4 objects shown in any view across a range of 135° anywhere in a scene. The model was able to generalize correctly within the four trained views and the 25 trained translations. This approach analyses the principles by which complementary computations in the dorsal and ventral visual cortical streams enable objects to be located and recognized in complex natural scenes. [ABSTRACT FROM AUTHOR]

When we see a human sitting down, standing up, or walking, we can recognize one of these poses independently of the individual, or we can recognize the individual person, independently of the pose. The same issues arise for deforming objects. For example, if we see a flag deformed by the wind, either blowing out or hanging languidly, we can usually recognize the flag, independently of its deformation; or we can recognize the deformation independently of the identity of the flag. We hypothesize that these types of recognition can be implemented by the primate visual system using temporo-spatial continuity as objects transform as a learning principle. In particular, we hypothesize that pose or deformation can be learned under conditions in which large numbers of different people are successively seen in the same pose, or objects in the same deformation. We also hypothesize that person-specific representations that are independent of pose, and object-specific representations that are independent of deformation and view, could be built, when individual people or objects are observed successively transforming from one pose or deformation and view to another. These hypotheses were tested in a simulation of the ventral visual system, VisNet, that uses temporal continuity, implemented in a synaptic learning rule with a short-term memory trace of previous neuronal activity, to learn invariant representations. It was found that depending on the statistics of the visual input, either pose-specific or deformation-specific representations could be built that were invariant with respect to individual and view; or that identity-specific representations could be built that were invariant with respect to pose or deformation and view. We propose that this is how pose-specific and pose-invariant, and deformation-specific and deformation-invariant, perceptual representations are built in the brain. [ABSTRACT FROM AUTHOR]

Texture may provide important clues for real world object and scene perception. For these clues to be reliable, they should ideally be invariant to common viewing variations such as changes in illumination and orientation. In a large image database of natural materials, we found textures with low-level contrast statistics that varied substantially under viewing variations, as well as textures that remained relatively constant. This led us to ask whether textures with constant contrast statistics give rise to more invariant representations compared to other textures. To test this, we selected natural texture images with either high (HV) or low (LV) variance in statistics and presented these to human observers. In two distinct behavioral categorization paradigms, participants more often judged HV textures as 'different' compared to LV textures, showing that textures with constant contrast statistics are perceived as being more invariant. In a separate EEG experiment, evoked responses to single texture images (single-image ERPs) were collected. The results show that differences in contrast statistics predicted both early and late differences in ERP amplitude between individual images. Importantly, ERP differences between images of HV textures were mainly driven by illumination angle, which was not the case for LV images: there, differences were completely driven by texture membership, as predicted by contrast statistics. These converging neural and behavioral results imply that some natural textures are surprisingly invariant and that low-level contrast statistics predict the extent of this invariance.

Neurophysiological evidence for invariant representations of objects and faces in the primate inferior temporal visual cortex is described. Then a computational approach to how invariant representations are formed in the brain is described that builds on the neurophysiology. A feature hierarchy modelin which invariant representations can be built by self-organizing learning based on the temporal and spatialstatistics of the visual input produced by objects as they transform in the world is described. VisNet can use temporal continuity in an associativesynaptic learning rule with a short term memory trace, and/or it can use spatialcontinuity in Continuous Spatial Transformation learning which does not require a temporal trace. The model of visual processing in theventral cortical stream can build representations of objects that are invariant withrespect to translation, view, size, and also lighting. The modelhas been extended to provide an account of invariant representations in the dorsal visualsystem of the global motion produced by objects such as looming, rotation, and objectbased movement. The model has been extended to incorporate top-down feedback connectionsto model the control of attention by biased competition in for example spatial and objectsearch tasks. The model has also been extended to account for how the visual system canselect single objects in complex visual scenes, and how multiple objects can berepresented in a scene. The model has also been extended to provide, with an additional layer, for the development of representations of spatial scenes of the type found in the hippocampus.

Learning by temporal association rules such as Foldiak’s trace rule is an attractive hypothesis that explains the development of invariance in visual recognition. Consistent with these rules, several recent experiments have shown that invariance can be broken at both the psychophysical and single cell levels. We show a) that temporal association learning provides appropriate invariance in models of object recognition inspired by the visual cortex, b) that we can replicate the invariance disruption experiments using these models with a temporal association learning rule to develop and maintain invariance, and c) that despite dramatic single cell effects, a population of cells is very robust to these disruptions. We argue that these models account for the stability of perceptual invariance despite the underlying plasticity of the system, the variability of the visual world and expected noise in the biological mechanisms.

Visual object recognition occurs easily despite differences in position, size, and rotation of the object, but the neural mechanisms responsible for this invariance are not known. We have found a set of transforms that achieve invariance in a neurally plausible way. We find that a transform based on local spatial frequency analysis of oriented segments and on logarithmic mapping, when applied twice in an iterative fashion, produces an output image that is unique to the object and that remains constant as the input image is shifted, scaled or rotated.

Learning by temporal association rules such as Foldiak's trace rule is an attractive hypothesis that explains the development of invariance in visual recognition. Consistent with these rules, several recent experiments have shown that invariance can be broken at both the psychophysical and single cell levels. We show (1) that temporal association learning provides appropriate invariance in models of object recognition inspired by the visual cortex, (2) that we can replicate the "invariance disruption" experiments using these models with a temporal association learning rule to develop and maintain invariance, and (3) that despite dramatic single cell effects, a population of cells is very robust to these disruptions. We argue that these models account for the stability of perceptual invariance despite the underlying plasticity of the system, the variability of the visual world and expected noise in the biological mechanisms. [ABSTRACT FROM AUTHOR]

Neurophysiological evidence for invariant representations of objects and faces in the primate inferior temporal visual cortex is described. Then a computational approach to how invariant representations are formed in the brain is described that builds on the neuro-physiology. A feature hierarchy model in which invariant representations can be built by self-organizing learning based on the temporal and spatial statistics of the visual input produced by objects as they transform in the world is described. VisNet can use temporal continuity in an associative synaptic learning rule with a short-term memory trace, and/or it can use spatial continuity in continuous spatial transformation learning which does not require a temporal trace. The model of visual processing in the ventral cortical stream can build representations of objects that are invariant with respect to translation, view, size, and also lighting. The model has been extended to provide an account of invariant representations in the dorsal visual system of the global motion produced by objects such as looming, rotation, and object-based movement. The model has been extended to incorporate top-down feedback connections to model the control of attention by biased competition in, for example, spatial and object search tasks.The approach has also been extended to account for how the visual system can select single objects in complex visual scenes, and how multiple objects can be represented in a scene. The approach has also been extended to provide, with an additional layer, for the development of representations of spatial scenes of the type found in the hippocampus. [ABSTRACT FROM AUTHOR]

Texture may provide important clues for real world object and scene perception. To be reliable, these clues should ideally be invariant to common viewing variations such as changes in illumination and orientation. In a large image database of natural materials, we found textures with low-level contrast statistics that varied substantially under viewing variations, as well as textures that remained relatively constant. This led us to ask whether textures with constant contrast statistics give rise to more invariant representations compared to other textures. To test this, we selected natural texture images with either high (HV) or low (LV) variance in contrast statistics and presented these to human observers. In two distinct behavioral categorization paradigms, participants more often judged HV textures as "different" compared to LV textures, showing that textures with constant contrast statistics are perceived as being more invariant. In a separate electroencephalogram (EEG) experiment, evoked responses to single texture images (single-image ERPs) were collected. The results show that differences in contrast statistics correlated with both early and late differences in occipital ERP amplitude between individual images. Importantly, ERP differences between images of HV textures were mainly driven by illumination angle, which was not the case for LV images: there, differences were completely driven by texture membership. These converging neural and behavioral results imply that some natural textures are surprisingly invariant to illumination changes and that low-level contrast statistics are diagnostic of the extent of this invariance. [ABSTRACT FROM AUTHOR]

An introduction is presented in which the editor discusses various reports within the issue on topics including visual object perception, object recognition and neural coding.

Learning by temporal association rules such as Foldiak's trace rule is an attractive hypothesis that explains the development of invariance in visual recognition. Consistent with these rules, several recent experiments have shown that invariance can be broken at both the psychophysical and single cell levels. We show (1) that temporal association learning provides appropriate invariance in models of object recognition inspired by the visual cortex, (2) that we can replicate the "invariance disruption" experiments using these models with a temporal association learning rule to develop and maintain invariance, and (3) that despite dramatic single cell effects, a population of cells is very robust to these disruptions. We argue that these models account for the stability of perceptual invariance despite the underlying plasticity of the system, the variability of the visual world and expected noise in the biological mechanisms.