End-to-End Instance Segmentation with Recurrent Attention
| Autor: | Richard S. Zemel, Mengye Ren |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
Closed captioning Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Image segmentation Object (computer science) Convolutional neural network Machine Learning (cs.LG) 030218 nuclear medicine & medical imaging Computer Science - Learning 03 medical and health sciences 0302 clinical medicine Recurrent neural network 0202 electrical engineering electronic engineering information engineering Question answering 020201 artificial intelligence & image processing Segmentation Graphical model Artificial intelligence business Structured prediction |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2017.39 |
| Popis: | While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance segmentation is very important in a variety of applications, such as autonomous driving, image captioning, and visual question answering. Techniques that combine large graphical models with low-level vision have been proposed to address this problem; however, we propose an end-to-end recurrent neural network (RNN) architecture with an attention mechanism to model a human-like counting process, and produce detailed instance segmentations. The network is jointly trained to sequentially produce regions of interest as well as a dominant object segmentation within each region. The proposed model achieves competitive results on the CVPPP, KITTI, and Cityscapes datasets. CVPR 2017 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|