Abstract

Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality. In this paper, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement. The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy -- pixel-, patch- and map- level -- by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersection-over-Union (IoU) losses. Equipped with the hybrid loss, the proposed predict-refine architecture is able to effectively segment the salient object regions and accurately predict the fine structures with clear boundaries. Experimental results on six public datasets show that our method outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures. Our method runs at over 25 fps on a single GPU. The code is available at: https://github.com/NathanUA/BASNet.

Keywords

Computer scienceArtificial intelligenceConvolutional neural networkSalientGround truthBoundary (topology)EncoderPattern recognition (psychology)Intersection (aeronautics)Object detectionCross entropyComputer visionTransformation (genetics)PixelResidualEntropy (arrow of time)AlgorithmMathematics

Affiliated Institutions

Related Publications

Publication Info

Year
2019
Type
article
Pages
7471-7481
Citations
1493
Access
Closed

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1493
OpenAlex
173
Influential
1255
CrossRef

Cite This

Xuebin Qin, Zichen Zhang, Chenyang Huang et al. (2019). BASNet: Boundary-Aware Salient Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 7471-7481. https://doi.org/10.1109/cvpr.2019.00766

Identifiers

DOI
10.1109/cvpr.2019.00766

Data Quality

Data completeness: 77%