MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
Authors:
- Peng WangPWPeng Wang
Preprint
Abstract
In this work, we tackle the problem of instance segmentation, the task of simultaneously solving object detection and semantic segmentation. Towards this goal, we present a model, called MaskLab, which produces three outputs: box detection, semantic segmentation, and direction prediction. Building on top of the Faster-RCNN object detector, the predicted boxes provide accurate localization of object instances. Within each region of interest, MaskLab performs foreground/background segmentation by combining semantic and direction prediction. Semantic segmentation assists the model in distinguishing between objects of different semantic classes including background, while the direction prediction, estimating each pixel's direction towards its corresponding center, allows separating instances of the same semantic class. Moreover, we explore the effect of incorporating recent successful methods from both segmentation and detection (i.e. atrous convolution and hypercolumn). Our proposed model is evaluated on the COCO instance segmentation benchmark and shows comparable performance with other state-of-art models.Keywords
All Related Versions
This publication has 55 references indexed in Scilit:
- Wider or Deeper: Revisiting the ResNet Model for Visual RecognitionPattern Recognition, 2019
- Learning to Refine Object Segments2016
- Higher Order Conditional Random Fields in Deep Neural Networks2016
- Recurrent Instance Segmentation2016
- Instance-Sensitive Fully Convolutional Networks2016
- Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling2016
- Multiscale Combinatorial Grouping2014
- Scalable Object Detection Using Deep Neural Networks2014
- Microsoft COCO: Common Objects in Context2014
- Simultaneous Detection and Segmentation2014