MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
arXiv:1712.04837
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.
10 pages including reference
References in corpus (9)
- Distilling the Knowledge in a Neural Network
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Semantic Instance Segmentation with a Discriminative Loss Function
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
- Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
- Semantic Instance Segmentation via Deep Metric Learning
- segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
- Object Detection Free Instance Segmentation With Labeling Transformations