Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection

Abstract

In this paper, we propose a novel edge preserving and multi-scale contextual neural network for salient object detection. The proposed framework is aiming to address two limits of the existing CNN based methods. First, region-based CNN methods lack sufficient context to accurately locate salient object since they deal with each region independently. Second, pixel-based CNN methods suffer from blurry boundaries due to the presence of convolutional and pooling layers. Motivated by these, we first propose an end-to-end edge-preserved neural network based on Fast R-CNN framework (named RegionNet) to efficiently generate saliency map with sharp object boundaries. Later, to further improve it, multi-scale spatial context is attached to RegionNet to consider the relationship between regions and the global scenes. Furthermore, our method can be generally applied to RGB-D saliency detection by depth refinement. The proposed framework achieves both clear detection boundary and multi-scale contextual robustness simultaneously for the first time, and thus achieves an optimized performance. Experiments on six RGB and two RGB-D benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Fully Convolutional Networks for Semantic Segmentation
• Salient Object Detection: A Benchmark
• Deeply-Supervised Nets
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
• Visual Saliency Based on Multiscale Deep Features
• Inner and Inter Label Propagation: Salient Object Detection in the Wild
• What is a salient object? A dataset and a baseline model for salient object detection
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• Convergent Learning: Do different neural networks learn the same representations?

Cited by in corpus (11)

• EDN: Salient Object Detection via Extremely-Downsampled Network
• Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images
• Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning
• Object Detection with Deep Learning: A Review
• Middle-level Fusion for Lightweight RGB-D Salient Object Detection
• Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
• Uncertainty Guided Refinement for Fine-Grained Salient Object Detection
• Edge-guided Non-local Fully Convolutional Network for Salient Object Detection
• Adaptive Fusion for RGB-D Salient Object Detection
• Hyperspectral Image Super-resolution via Deep Spatio-spectral Convolutional Neural Networks
• Unsupervised segmentation via semantic-apparent feature fusion