# Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs

arXiv: https://arxiv.org/abs/1608.05186 · HTML: https://mlsanity.com/paper/1608.05186/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2016.

## Built on by (most cited first, 5 of 5)

- [Advances in Deep Concealed Scene Understanding](https://mlsanity.com/paper/2304.11234/) (2023)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Superpixel-based Refinement for Object Proposal Generation](https://mlsanity.com/paper/2101.04574/) (2021)
- [Unsupervised Learning for Target Tracking and Background Subtraction in Satellite Imagery](https://mlsanity.com/paper/2109.00885/) (2021)
- [Semi-Supervised Cross-Modal Salient Object Detection with U-Structure Networks](https://mlsanity.com/paper/2208.04361/) (2022)

## Abstract (arXiv)

This paper proposes a novel saliency detection method by combining region-level saliency estimation and pixel-level saliency prediction with CNNs (denoted as CRPSD). For pixel-level saliency prediction, a fully convolutional neural network (called pixel-level CNN) is constructed by modifying the VGGNet architecture to perform multi-scale feature learning, based on which an image-to-image prediction is conducted to accomplish the pixel-level saliency detection. For region-level saliency estimation, an adaptive superpixel based region generation technique is first designed to partition an image into regions, based on which the region-level saliency is estimated by using a CNN model (called region-level CNN). The pixel-level and region-level saliencies are fused to form the final salient map by using another CNN (called fusion CNN). And the pixel-level CNN and fusion CNN are jointly learned. Extensive quantitative and qualitative experiments on four public benchmark datasets demonstrate that the proposed method greatly outperforms the state-of-the-art saliency detection approaches.