Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton

Abstract

In this paper, we solve three low-level pixel-wise vision problems, including salient object segmentation, edge detection, and skeleton extraction, within a unified framework. We first show some similarities shared by these tasks and then demonstrate how they can be leveraged for developing a unified framework that can be trained end-to-end. In particular, we introduce a selective integration module that allows each task to dynamically choose features at different levels from the shared backbone based on its own characteristics. Furthermore, we design a task-adaptive attention module, aiming at intelligently allocating information for different tasks according to the image content priors. To evaluate the performance of our proposed network on these tasks, we conduct exhaustive experiments on multiple representative datasets. We will show that though these tasks are naturally quite different, our network can work well on all of them and even perform better than current single-purpose state-of-the-art methods. In addition, we also conduct adequate ablation analyses that provide a full understanding of the design principles of the proposed framework. To facilitate future research, source code will be released.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Improving neural networks by preventing co-adaptation of feature detectors
• Res2Net: A New Multi-scale Backbone Architecture
• Squeeze-and-Excitation Networks
• 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
• GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• Learning Task Grouping and Overlap in Multi-task Learning
• Salient Object Detection: A Discriminative Regional Feature Integration Approach
• Channel Gating Neural Networks
• R-CNNs for Pose Estimation and Action Detection
• DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
• Pixel-wise Deep Learning for Contour Detection
• SRN: Side-output Residual Network for Object Symmetry Detection in the Wild

Cited by in corpus (8)

• CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection
• Salient Objects in Clutter
• View-aware Salient Object Detection for 360° Omnidirectional Image
• Pixel Difference Networks for Efficient Edge Detection
• FakeMix Augmentation Improves Transparent Object Detection
• Centralized Information Interaction for Salient Object Detection
• Receptive Field Broadening and Boosting for Salient Object Detection
• Complementary Segmentation of Primary Video Objects with Reversible Flows