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

arXiv: https://arxiv.org/abs/1804.07836 · HTML: https://mlsanity.com/paper/1804.07836/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2018.

## Built on by (most cited first, 15 of 15)

- [Radar-Camera Pixel Depth Association for Depth Completion](https://mlsanity.com/paper/2106.02778/) (2021)
- [Directional Connectivity-based Segmentation of Medical Images](https://mlsanity.com/paper/2304.00145/) (2023)
- [Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM](https://mlsanity.com/paper/2404.04996/) (2024)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Full-Velocity Radar Returns by Radar-Camera Fusion](https://mlsanity.com/paper/2108.10637/) (2021)
- [BiconNet: An Edge-preserved Connectivity-based Approach for Salient Object Detection](https://mlsanity.com/paper/2103.00334/) (2021)
- [Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes](https://mlsanity.com/paper/2203.04031/) (2022)
- [Instance-Level Relative Saliency Ranking with Graph Reasoning](https://mlsanity.com/paper/2107.03824/) (2021)
- [NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2201.03686/) (2022)
- [Spatial Coherence Loss: All Objects Matter in Salient and Camouflaged Object Detection](https://mlsanity.com/paper/2402.18698/) (2024)
- [Learning Physical Dynamics for Object-centric Visual Prediction](https://mlsanity.com/paper/2403.10079/) (2024)
- [BuyTheDips: PathLoss for improved topology-preserving deep learning-based image segmentation](https://mlsanity.com/paper/2207.11446/) (2022)
- [Fine-Grained Extraction of Road Networks via Joint Learning of Connectivity and Segmentation](https://mlsanity.com/paper/2312.04744/) (2023)
- [DCFFSNet: Deep Connectivity Feature Fusion Separation Network for Medical Image Segmentation](https://mlsanity.com/paper/2507.18407/) (2025)
- [RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction](https://mlsanity.com/paper/2605.26862/) (2026)

## Abstract (arXiv)

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.