Instance-Level Salient Object Segmentation

CVPR 2017  ·  Guanbin Li, Yuan Xie, Liang Lin, Yizhou Yu ·

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.

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract

Results from the Paper


Ranked #17 on RGB Salient Object Detection on DUTS-TE (max F-measure metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
RGB Salient Object Detection DUTS-TE MSR MAE 0.062 # 25
max F-measure 0.824 # 17

Methods


No methods listed for this paper. Add relevant methods here