Instance-Level Salient Object Segmentation

TL;DR

This paper introduces a novel deep learning-based method for salient instance segmentation that identifies individual salient objects within images, outperforming existing methods and supported by a new annotated dataset.

Contribution

The paper presents a multiscale saliency refinement network combined with grouping and optimization techniques for the first time in salient instance segmentation, along with a new annotated dataset.

Findings

Achieves state-of-the-art results on public salient region detection benchmarks.

Demonstrates high-quality salient object instance segmentation on the new dataset.

Outperforms previous methods in both saliency detection and instance segmentation tasks.

Abstract

Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks. However, none of the existing methods is able to identify object instances in the detected salient regions. In this paper, we present a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image. Our method consists of three steps, estimating saliency map, detecting salient object contours and identifying salient object instances. For the first two steps, we propose a multiscale saliency refinement network, which generates high-quality salient region masks and salient object contours. Once integrated with multiscale combinatorial grouping and a MAP-based subset optimization framework, our method can generate very promising salient object instance segmentation results. To promote further research and evaluation of salient instance segmentation, we also construct a new database of 1000 images and their pixelwise salient instance annotations. Experimental results demonstrate that our proposed method is capable of achieving state-of-the-art performance on all public benchmarks for salient region detection as well as on our new dataset for salient instance segmentation.