Dissociated Dipoles: Image representation via non-local comparisons
Author(s)Balas, Benjamin J.; Sinha, Pawan
A fundamental question in visual neuroscience is how to represent image structure. The most common representational schemes rely on differential operators that compare adjacent image regions. While well-suited to encoding local relationships, such operators have significant drawbacks. Specifically, each filterÂs span is confounded with the size of its sub-fields, making it difficult to compare small regions across large distances. We find that such long-distance comparisons are more tolerant to common image transformations than purely local ones, suggesting they may provide a useful vocabulary for image encoding. .We introduce the ÂDissociated Dipole,Â or ÂSticksÂ operator, for encoding non-local image relationships. This operator de-couples filter span from sub-field size, enabling parametric movement between edge and region-based representation modes. We report on the perceptual plausibility of the operator, and the computational advantages of non-local encoding. Our results suggest that non-local encoding may be an effective scheme for representing image structure.
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
AI, image representation, recognition, non-local filtering