BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks

By Viet Quoc Pham, Satoshi Ito, Tatsuo Kozakaya. 2017

15 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ross B. Girshick
2. Kaiming He
3. Piotr Doll'ar
4. Alexander Kirillov
5. Dacheng Tao
6. Quoc V. Le
7. Alan L. Yuille
8. Trevor Darrell

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Ling Shao
3. Luc Van Gool
4. Xuelong Li
5. Kaiming He
6. Ross B. Girshick
7. Xiaogang Wang
8. Jitendra Malik

In Control and Systems Engineering

1. Yanwei Pang
2. Jiale Cao
3. Ross B. Girshick
4. Kaiming He
5. Xuelong Li

Citations in the corpus

• Panoptic Feature Pyramid Networks (2019, background): “While there have been attempts to unify semantic and instance segmentation [46, 1, 9], the specialization currently necessary to achieve top performance in each was perhaps inevitable given their parallel development and separate benchmarks.”
• Triply Supervised Decoder Networks for Joint Detection and Segmentation (2018, methodology): “Meanwhile, joint instance semantic segmentation and object detection is proposed [40, 39].”