BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks
This addresses the problem of efficient and accurate segmentation for computer vision applications, but it is incremental as it builds on existing FCN and position-sensitive score map methods.
The paper tackles simultaneous semantic and instance segmentation by proposing BiSeg, a fully convolutional network framework that uses Bayesian inference with semantic segmentation as a prior and multi-scale fusion as a likelihood, achieving state-of-the-art accuracy on PASCAL VOC.
We present a simple and effective framework for simultaneous semantic segmentation and instance segmentation with Fully Convolutional Networks (FCNs). The method, called BiSeg, predicts instance segmentation as a posterior in Bayesian inference, where semantic segmentation is used as a prior. We extend the idea of position-sensitive score maps used in recent methods to a fusion of multiple score maps at different scales and partition modes, and adopt it as a robust likelihood for instance segmentation inference. As both Bayesian inference and map fusion are performed per pixel, BiSeg is a fully convolutional end-to-end solution that inherits all the advantages of FCNs. We demonstrate state-of-the-art instance segmentation accuracy on PASCAL VOC.