Enhancing Generic Segmentation with Learned Region Representations
This addresses the gap in applying deep learning directly to generic segmentation, offering a novel approach that enhances performance for tasks requiring non-semantic segmentation.
The paper tackles the problem of generic segmentation by proposing a method that learns pixel-wise representations reflecting segment relatedness, achieving state-of-the-art segment similarity scores and improving overall segmentation quality in most measures.
Current successful approaches for generic (non-semantic) segmentation rely mostly on edge detection and have leveraged the strengths of deep learning mainly by improving the edge detection stage in the algorithmic pipeline. This is in contrast to semantic and instance segmentation, where DNNs are applied directly to generate pixel-wise segment representations. We propose a new method for learning a pixel-wise representation that reflects segment relatedness. This representation is combined with an edge map to yield a new segmentation algorithm. We show that the representations themselves achieve state-of-the-art segment similarity scores. Moreover, the proposed combined segmentation algorithm provides results that are either state of the art or improve upon it, for most quality measures.