Abstract

Convolutional-deconvolution networks can be adoptedto perform end-to-end saliency detection. But, they do notwork well with objects of multiple scales. To overcomesuch a limitation, in this work, we propose a recurrent at-tentional 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 en-hance saliency refinement in future iterations. Experimentson several challenging saliency detection datasets validate the effectiveness of RACDNN, and show that RACDNN outperforms state-of-the-art saliency detection methods.