ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
Preprint
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 improvements can be obtained by modeling these tasks as connectivity instead of binary segmentation tasks. We achieve state-of-the-art performance, outperforming or being comparable to existing approaches while reducing training time due to our less complex approach.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Proposal-Free Network for Instance-Level Object SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Global Contrast Based Salient Region DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Fusing generic objectness and visual saliency for salient object detection2011