Improving spatial codification in semantic segmentation
International Conference on Image Processing, pp. 3605-3609, 2015.
This paper explores novel approaches for improving the spatial codification for the pooling of local descriptors to solve the semantic segmentation problem. We propose to partition the image into three regions for each object to be described: Figure, Border and Ground. This partition aims at minimizing the influence of the image context...More
PPT (Upload PPT)