Towards High-Resolution Salient Object Detection
About
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 ($400\times400$ 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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Salient Object Detection | DUTS (test) | M (MAE)0.05 | 302 | |
| Salient Object Detection | ECSSD | MAE0.052 | 202 | |
| Salient Object Detection | PASCAL-S | MAE0.079 | 186 | |
| Salient Object Detection | HKU-IS | MAE0.042 | 155 | |
| Salient Object Detection | DUT-OMRON | MAE0.065 | 120 | |
| Salient Object Detection | HRSOD (test) | F-beta0.905 | 65 | |
| Salient Object Detection | DAVIS S | F_beta89.9 | 36 | |
| Salient Object Detection | THUR | F-beta Score74.9 | 22 | |
| Salient Object Detection | DAVIS-S high-resolution (test) | Fmax89.9 | 20 | |
| Salient Object Detection | DUTS low-resolution (test) | Fmax0.801 | 20 |