English

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

Computer Vision and Pattern Recognition 2019-02-13 v2

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.

Keywords

Cite

@article{arxiv.1804.07836,
  title  = {ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation},
  author = {Michael Kampffmeyer and Nanqing Dong and Xiaodan Liang and Yujia Zhang and Eric P. Xing},
  journal= {arXiv preprint arXiv:1804.07836},
  year   = {2019}
}
R2 v1 2026-06-23T01:30:38.842Z