English

Towards High-Resolution Salient Object Detection

Computer Vision and Pattern Recognition 2019-08-21 v1

Abstract

Deep neural network based methods have made a significant breakthrough in salient object detection. However, they are typically limited to input images with low resolutions (400×400400\times400 pixels or less). Little effort has been made to train deep neural networks to directly handle salient object detection in very high-resolution images. This paper pushes forward high-resolution saliency detection, and contributes a new dataset, named High-Resolution Salient Object Detection (HRSOD). To our best knowledge, HRSOD is the first high-resolution saliency detection dataset to date. As another contribution, we also propose a novel approach, which incorporates both global semantic information and local high-resolution details, to address this challenging task. More specifically, our approach consists of a Global Semantic Network (GSN), a Local Refinement Network (LRN) and a Global-Local Fusion Network (GLFN). GSN extracts the global semantic information based on down-sampled entire image. Guided by the results of GSN, LRN focuses on some local regions and progressively produces high-resolution predictions. GLFN is further proposed to enforce spatial consistency and boost performance. Experiments illustrate that our method outperforms existing state-of-the-art methods on high-resolution saliency datasets by a large margin, and achieves comparable or even better performance than them on widely-used saliency benchmarks. The HRSOD dataset is available at https://github.com/yi94code/HRSOD.

Keywords

Cite

@article{arxiv.1908.07274,
  title  = {Towards High-Resolution Salient Object Detection},
  author = {Yi Zeng and Pingping Zhang and Jianming Zhang and Zhe Lin and Huchuan Lu},
  journal= {arXiv preprint arXiv:1908.07274},
  year   = {2019}
}

Comments

Accepted by ICCV2019. The HRSOD dataset is available at https://github.com/yi94code/HRSOD

R2 v1 2026-06-23T10:51:59.467Z