Salient Object Detection using a Context-Aware Refinement Network

Md Amirul Amirul, Mahmoud Kalash, Mrigank Rochan, Neil Bruce and Yang Wang

Abstract

Recently there has been remarkable success in pushing the state of the art in salient object detection. Most of the improvements are driven by employing end-to-end deeper feed-forward networks. However, in many cases precisely detecting salient regions requires representation of fine details. Combining high-level and low-level features using skip connections is a strategy that has been proposed, but sometimes fails to select the right contextual features. To overcome this limitation, we propose an end-to-end encoder-decoder network that employs recurrent refinement to generate a saliency map in a coarse-to-fine fashion by incorporating finer details in the detection framework. The proposed approach makes use of refinement units within each stage of the decoder that are responsible for refining the saliency map produced by earlier layers by learning context-aware features.

Session

Posters

Files

Paper (PDF)

DOI

10.5244/C.31.61
https://dx.doi.org/10.5244/C.31.61

Citation

Bibtex

            @inproceedings{BMVC2017_61,
                title={Salient Object Detection using a Context-Aware Refinement Network},
                author={Md Amirul Amirul, Mahmoud Kalash, Mrigank Rochan, Neil Bruce and Yang Wang},
                year={2017},
                month={September},
                pages={61.1-61.12},
                articleno={61},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.61},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.61}
            }