Instance-Aware Semantic Segmentation via Multi-task Network Cascades

Semantic segmentation research has recently witnessed rapid progress, but many leading methods are unable to identify object instances. In this paper, we present Multitask Network Cascades for instance-aware semantic segmentation. Our model consists of three networks, respectively differentiating in...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) S. 3150 - 3158
Hauptverfasser: Jifeng Dai, Kaiming He, Jian Sun
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2016
Schlagworte:
Backpropagation
Feature extraction
Image segmentation
Object detection
Proposals
Semantics
Training
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Semantic segmentation research has recently witnessed rapid progress, but many leading methods are unable to identify object instances. In this paper, we present Multitask Network Cascades for instance-aware semantic segmentation. Our model consists of three networks, respectively differentiating instances, estimating masks, and categorizing objects. These networks form a cascaded structure, and are designed to share their convolutional features. We develop an algorithm for the nontrivial end-to-end training of this causal, cascaded structure. Our solution is a clean, single-step training framework and can be generalized to cascades that have more stages. We demonstrate state-of-the-art instance-aware semantic segmentation accuracy on PASCAL VOC. Meanwhile, our method takes only 360ms testing an image using VGG-16, which is two orders of magnitude faster than previous systems for this challenging problem. As a by product, our method also achieves compelling object detection results which surpass the competitive Fast/Faster R-CNN systems. The method described in this paper is the foundation of our submissions to the MS COCO 2015 segmentation competition, where we won the 1st place.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.343