Learning Location Invariance for Object Recognition and Localization
نویسندگان
چکیده
A visual system not only needs to recognize a stimulus, it also needs to find the location of the stimulus. In this paper, we present a neural network model that is able to generalize its ability to identify objects to new locations in its visual field. The model consists of a feedforward network for object identification and a feedback network for object location. The feedforward network first learns to identify simple features at all locations and therefore becomes selective for location invariant features. This network subsequently learns to identify objects partly by learning new conjunctions of these location invariant features. Once the feedforward network is able to identify an object at a new location, all conditions for supervised learning of additional, location dependent features for the object are set. The learning in the feedforward network can be transferred to the feedback network, which is needed to localize an object at a new location.
منابع مشابه
Low-level global features for vision-based localizations
Vision-based self-localization is the ability to derive one’s own location from visual input only without knowledge of a previous position or idiothetic information. It is often assumed that the visual mechanisms and invariance properties used for object recognition will also be helpful for localization. Here we show that this is neither logically reasonable nor empirically supported. We argue ...
متن کاملApplication of Combined Local Object Based Features and Cluster Fusion for the Behaviors Recognition and Detection of Abnormal Behaviors
In this paper, we propose a novel framework for behaviors recognition and detection of certain types of abnormal behaviors, capable of achieving high detection rates on a variety of real-life scenes. The new proposed approach here is a combination of the location based methods and the object based ones. First, a novel approach is formulated to use optical flow and binary motion video as the loc...
متن کاملCategory learning induces position invariance of pattern recognition across the visual field.
Human object recognition is considered to be largely invariant to translation across the visual field. However, the origin of this invariance to positional changes has remained elusive, since numerous studies found that the ability to discriminate between visual patterns develops in a largely location-specific manner, with only a limited transfer to novel visual field positions. In order to rec...
متن کاملProceedings of the KI 2013 Workshop on Visual and Spatial Cognition
Vision-based self-localization is the ability to derive one’s own location from visual input only without knowledge of a previous position or idiothetic information. It is often assumed that the visual mechanisms and invariance properties used for object recognition will also be helpful for localization. Here we show that this is neither logically reasonable nor empirically supported. We argue ...
متن کاملJ . S . , Vankov , I . , & Ludwig , C . J . H . ( 2016 ) . The visual system supports on - line translation invariance for object identification
The ability to recognize the same image projected to different retinal locations is critical for visual object recognition in naturalist contexts. On many theories translation invariance for objects only extends to trained retinal locations. On this approach, a familiar object projected to a non-trained location should not be identified. On another approach invariance is achieved “on-line”, suc...
متن کامل