ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation

Abstract

Salient segmentation aims to segment out attention-grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and benefits from the utilization of global multi-scale contexts to achieve good local reasoning. Previous works often address it as two-class segmentation problems utilizing complicated multi-step procedures including refinement networks and complex graphical models. We argue that semantic salient segmentation can instead be effectively resolved by reformulating it as a simple yet intuitive pixel-pair based connectivity prediction task. Following the intuition that salient objects can be naturally grouped via semantic-aware connectivity between neighboring pixels, we propose a pure Connectivity Net (ConnNet). ConnNet predicts connectivity probabilities of each pixel with its neighboring pixels by leveraging multi-level cascade contexts embedded in the image and long-range pixel relations. We investigate our approach on two tasks, namely salient object segmentation and salient instance-level segmentation, and illustrate that consistent improvements can be obtained by modeling these tasks as connectivity instead of binary segmentation tasks for a variety of network architectures. We achieve state-of-the-art performance, outperforming or being comparable to existing approaches while reducing inference time due to our less complex approach.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Fully Convolutional Networks for Semantic Segmentation
• Deeply supervised salient object detection with short connections
• SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
• Proposal-free Network for Instance-level Object Segmentation
• Supervised Adversarial Networks for Image Saliency Detection

Cited by in corpus (13)

• CAGNet: Content-Aware Guidance for Salient Object Detection
• PaDNet: Pan-Density Crowd Counting
• Optimized Deep Encoder-Decoder Methods for Crack Segmentation
• Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes
• NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery
• Salient Objects in Clutter
• Context-Integrated and Feature-Refined Network for Lightweight Object Parsing
• Enhance Connectivity of Promising Regions for Sampling-based Path Planning
• Instance-Level Relative Saliency Ranking with Graph Reasoning
• BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection
• A Cost Effective Solution for Road Crack Inspection using Cameras and Deep Neural Networks
• Radar-Camera Pixel Depth Association for Depth Completion
• Fully Automated 3D Segmentation of MR-Imaged Calf Muscle Compartments: Neighborhood Relationship Enhanced Fully Convolutional Network