Recurrent Attentional Networks for Saliency Detection

Abstract

Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection. But, they do not work well with objects of multiple scales. To overcome such a limitation, in this work, we propose a recurrent attentional convolutional-deconvolution network (RACDNN). Using spatial transformer and recurrent network units, RACDNN is able to iteratively attend to selected image sub-regions to perform saliency refinement progressively. Besides tackling the scale problem, RACDNN can also learn context-aware features from past iterations to enhance saliency refinement in future iterations. Experiments on several challenging saliency detection datasets validate the effectiveness of RACDNN, and show that RACDNN outperforms state-of-the-art saliency detection methods.

arXiv commentCVPR 2016

References in corpus (2)

• Recurrent Models of Visual Attention
• Recent Advances in Convolutional Neural Networks

Cited by in corpus (11)

• Multi-label Image Recognition by Recurrently Discovering Attentional Regions
• Crowd Counting using Deep Recurrent Spatial-Aware Network
• Co-salient Object Detection Based on Deep Saliency Networks and Seed Propagation over an Integrated Graph
• Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction
• Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition
• An Empirical Study of Language CNN for Image Captioning
• An Attention-Driven Approach of No-Reference Image Quality Assessment
• Contrast-Oriented Deep Neural Networks for Salient Object Detection
• A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection
• CRAM: Clued Recurrent Attention Model
• Weakly Supervised Domain-Specific Color Naming Based on Attention