Revisiting Graph Construction for Fast Image Segmentation
This work addresses the problem of efficient image segmentation for computer vision applications, presenting an incremental improvement over existing methods.
The paper tackles fast image segmentation by constructing a graph with global and local connections based on region co-occurrence and visual saliency, achieving competitive accuracy and significantly improved efficiency on benchmarks like BSDS500, PASCAL VOC, and COCO.
In this paper, we propose a simple but effective method for fast image segmentation. We re-examine the locality-preserving character of spectral clustering by constructing a graph over image regions with both global and local connections. Our novel approach to build graph connections relies on two key observations: 1) local region pairs that co-occur frequently will have a high probability to reside on a common object; 2) spatially distant regions in a common object often exhibit similar visual saliency, which implies their neighborship in a manifold. We present a novel energy function to efficiently conduct graph partitioning. Based on multiple high quality partitions, we show that the generated eigenvector histogram based representation can automatically drive effective unary potentials for a hierarchical random field model to produce multi-class segmentation. Sufficient experiments, on the BSDS500 benchmark, large-scale PASCAL VOC and COCO datasets, demonstrate the competitive segmentation accuracy and significantly improved efficiency of our proposed method compared with other state of the arts.