Multi-scale region-based saliency detection using W2 distance on N-dimensional normal distributions

We present a new segment-based method for saliency detection based on multi-size superpixels that combines local and global saliency cues. We extract superpixels at several scales and represent each superpixel with a normal distribution in CIE-Lab space estimated from its associated pixels. Global saliency is computed by grouping similar superpixels to estimate the spatial distribution of colors, while local saliency detection is achieved by determining the center-surround contrast of neighboring superpixels. Both methods rely on the Wasserstein distance on L₂ norm (W₂) to measure perceptual (dis-)similarity between superpixels. Additionally, we propose a Saliency Flow technique to refine the local saliency map. Our approach uses very few empirical parameters and outperforms 6 recent state-of-the-art saliency detection methods in terms of several evaluations on a widely used benchmark.