2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017
DOI: 10.1109/cvpr.2017.70
|View full text |Cite
|
Sign up to set email alerts
|

Boundary-Aware Instance Segmentation

Abstract: We address the problem of instance-level semantic segmentation, which aims at jointly detecting, segmenting and classifying every individual object in an image. In this context, existing methods typically propose candidate objects, usually as bounding boxes, and directly predict a binary mask within each such proposal. As a consequence, they cannot recover from errors in the object candidate generation process, such as too small or shifted boxes.In this paper, we introduce a novel object segment representation… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
91
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 155 publications
(91 citation statements)
references
References 30 publications
(84 reference statements)
0
91
0
Order By: Relevance
“…In [17] a simultaneous detection and segmentation algorithm is developed that classifies and refines CNN features obtained from regions under R-CNN [16] bounding box proposals. The work in [18] emphasizes on refining object boundaries for binary segmentation masks initially generated from bounding box proposals. In [12] a multi-task network cascade is introduced that, beyond sharing features from the encoder in all following tasks, subsequently adds blocks for i) bounding box generation, ii) instance mask generation and iii) mask categorization.…”
Section: Related Workmentioning
confidence: 99%
“…In [17] a simultaneous detection and segmentation algorithm is developed that classifies and refines CNN features obtained from regions under R-CNN [16] bounding box proposals. The work in [18] emphasizes on refining object boundaries for binary segmentation masks initially generated from bounding box proposals. In [12] a multi-task network cascade is introduced that, beyond sharing features from the encoder in all following tasks, subsequently adds blocks for i) bounding box generation, ii) instance mask generation and iii) mask categorization.…”
Section: Related Workmentioning
confidence: 99%
“…Lin et al [29] propose a multi-resolution approach for object detection which they call feature pyramid networks. In [16], the region proposals are refined with network that predicts the distance to the boundary which is then transformed into a binary object mask. Khoreva et al [20] jointly perform instance and semantic segmentation.…”
Section: Related Workmentioning
confidence: 99%
“…The MNC approach [10], based on Faster-RCNN [47], repeats this process twice [10] while [33] does it multiple times. [22] extends [10] to model the shape of objects. The fully convolutional instance segmentation method of [32] also combines segmentation proposal and object detection using a position sensitive score map.…”
Section: Related Workmentioning
confidence: 99%