# Recurrent Attentional Networks for Saliency Detection

arXiv: https://arxiv.org/abs/1604.03227 · HTML: https://mlsanity.com/paper/1604.03227/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2016.

## Built on by (most cited first, 11 of 11)

- [Differentiable Patch Selection for Image Recognition](https://mlsanity.com/paper/2104.03059/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Boundary-Aware Segmentation Network for Mobile and Web Applications](https://mlsanity.com/paper/2101.04704/) (2021)
- [TRACER: Extreme Attention Guided Salient Object Tracing Network](https://mlsanity.com/paper/2112.07380/) (2021)
- [Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal](https://mlsanity.com/paper/2103.07051/) (2021)
- [Recursive Contour Saliency Blending Network for Accurate Salient Object Detection](https://mlsanity.com/paper/2105.13865/) (2021)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Instance-Level Relative Saliency Ranking with Graph Reasoning](https://mlsanity.com/paper/2107.03824/) (2021)
- [Relevance for Human Robot Collaboration](https://mlsanity.com/paper/2409.07753/) (2024)
- [Beyond the Gates of Euclidean Space: Temporal-Discrimination-Fusions and Attention-based Graph Neural Network for Human Activity Recognition](https://mlsanity.com/paper/2206.04855/) (2022)
- [Spatial Attention-based Distribution Integration Network for Human Pose Estimation](https://mlsanity.com/paper/2311.05323/) (2023)

## Abstract (arXiv)

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.