Enhancing Generic Segmentation with Learned Region Representations

TL;DR

This paper introduces a novel pixel-wise representation for generic segmentation that, when combined with edge detection, achieves state-of-the-art results and improves segmentation quality across multiple metrics.

Contribution

The paper proposes a new learned region representation for generic segmentation, enhancing existing edge-based methods and surpassing previous performance benchmarks.

Findings

Representation achieves state-of-the-art segment similarity scores.

Combined algorithm outperforms existing methods on multiple quality measures.

Method improves segmentation accuracy without relying solely on edge detection.

Abstract

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.