Wu, Y.-H., Liu, Y., Zhang, L., Gao, W., & Cheng, M.-M. (2021). Regularized Densely-Connected Pyramid Network for Salient Instance Segmentation. IEEE Transactions on Image Processing, 30, 3897–3907. doi:10.1109/tip.2021.3065822
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 state-of-the-art 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 .
This research was supported by the Major Project for New Generation of AI under Grant No. 2018AAA0100400, S&T innovation project from Chinese Ministry of Education, and NSFC (61922046).