Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

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 \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.

arXiv commentAccepted in IEEE Transactions on Image Processing. Code: https://github.com/yuhuan-wu/RDPNet

References in corpus (10)

• UnitBox: An Advanced Object Detection Network
• Salient Object Detection: A Benchmark
• Richer Convolutional Features for Edge Detection
• Deeply supervised salient object detection with short connections
• Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
• Salient Object Detection: A Survey
• Convolutional Feature Masking for Joint Object and Stuff Segmentation
• JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation
• Salient Object Detection: A Discriminative Regional Feature Integration Approach
• Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss

Cited by in corpus (6)

• P2T: Pyramid Pooling Transformer for Scene Understanding
• EDN: Salient Object Detection via Extremely-Downsampled Network
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Advances in Deep Concealed Scene Understanding
• CPP-Net: Context-aware Polygon Proposal Network for Nucleus Segmentation
• Salient Objects in Clutter