Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance segmentation (SIS) that predicts a class-agnostic mask for each detected salient instance. To better use the rich feature hierarchies in deep networks and enhance the side predictions, we propose the regularized dense connections, which attentively promote informative features and suppress non-informative ones from all feature pyramids. A novel multi-level RoIAlign based decoder is introduced to adaptively aggregate multi-level features for better mask predictions. Such strategies can be well-encapsulated into the Mask R-CNN pipeline. Extensive experiments on popular benchmarks demonstrate that our design significantly outperforms existing \sArt competitors by 6.3\% (58.6\% vs. 52.3\%) in terms of the AP metric.The code is available at https://github.com/yuhuan-wu/RDPNet.
@article{arxiv.2008.12416,
title = {Regularized Densely-connected Pyramid Network for Salient Instance Segmentation},
author = {Yu-Huan Wu and Yun Liu and Le Zhang and Wang Gao and Ming-Ming Cheng},
journal= {arXiv preprint arXiv:2008.12416},
year = {2021}
}
Comments
Accepted in IEEE Transactions on Image Processing. Code: https://github.com/yuhuan-wu/RDPNet