Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss

Abstract

Salient object detection (SOD), which aims to identify and locate the most salient pixels or regions in images, has been attracting more and more interest due to its various real-world applications. However, this vision task is quite challenging, especially under complex image scenes. Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection. Specifically, we design a symmetrical fully convolutional network (SFCN) to effectively learn complementary saliency features under the guidance of lossless feature reflection. The location information, together with contextual and semantic information, of salient objects are jointly utilized to supervise the proposed network for more accurate saliency predictions. In addition, to overcome the blurry boundary problem, we propose a new weighted structural loss function to ensure clear object boundaries and spatially consistent saliency. The coarse prediction results are effectively refined by these structural information for performance improvements. Extensive experiments on seven saliency detection datasets demonstrate that our approach achieves consistently superior performance and outperforms the very recent state-of-the-art methods with a large margin.

To appear in IEEE Transaction on Image Processing. This paper is extended from arXiv:1802.06527

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Two-Stream Convolutional Networks for Action Recognition in Videos
• An overview of gradient descent optimization algorithms
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Fully Convolutional Networks for Semantic Segmentation
• Salient Object Detection: A Benchmark
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Revisiting Batch Normalization For Practical Domain Adaptation
• What is a salient object? A dataset and a baseline model for salient object detection
• Boundary-guided Feature Aggregation Network for Salient Object Detection
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Interactive Deep Colorization With Simultaneous Global and Local Inputs

Cited by in corpus (11)

• Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
• Bilateral Attention Network for RGB-D Salient Object Detection
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Hierarchical Paired Channel Fusion Network for Street Scene Change Detection
• SAC-Net: Spatial Attenuation Context for Salient Object Detection
• EGNet:Edge Guidance Network for Salient Object Detection
• Salient Objects in Clutter
• Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
• Towards High-Resolution Salient Object Detection
• Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detection
• A Deep Ordinal Distortion Estimation Approach for Distortion Rectification