Regularized Densely-Connected Pyramid Network for Salient Instance Segmentation

Page view(s)
28
Checked on Nov 29, 2024
Regularized Densely-Connected Pyramid Network for Salient Instance Segmentation
Title:
Regularized Densely-Connected Pyramid Network for Salient Instance Segmentation
Journal Title:
IEEE Transactions on Image Processing
Publication Date:
22 March 2021
Citation:
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
Abstract:
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 .
License type:
Publisher Copyright
Funding Info:
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).
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1057-7149
1941-0042
Files uploaded:

File Size Format Action
21tipinstsal.pdf 3.34 MB PDF Open