SAC-Net: Spatial Attenuation Context for Salient Object Detection

Abstract

This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects. Our key idea is to adaptively propagate and aggregate the image context features with variable attenuation over the entire feature maps. To achieve this, we design the spatial attenuation context (SAC) module to recurrently translate and aggregate the context features independently with different attenuation factors and then to attentively learn the weights to adaptively integrate the aggregated context features. By further embedding the module to process individual layers in a deep network, namely SAC-Net, we can train the network end-to-end and optimize the context features for detecting salient objects. Compared with 29 state-of-the-art methods, experimental results show that our method performs favorably over all the others on six common benchmark data, both quantitatively and visually.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Salient Object Detection: A Benchmark
• Deeply supervised salient object detection with short connections
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
• Object-Part Attention Model for Fine-grained Image Classification
• Direction-aware Spatial Context Features for Shadow Detection
• Direction-aware Spatial Context Features for Shadow Detection and Removal
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss

Cited by in corpus (6)

• SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection
• HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection
• Boundary-Aware Segmentation Network for Mobile and Web Applications
• Salient Objects in Clutter
• Unifying Global-Local Representations in Salient Object Detection with Transformer
• Weakly-Supervised Saliency Detection via Salient Object Subitizing