Deep Affinity Net: Instance Segmentation via Affinity release_7u2yidtuwbcdjidvkt7p2knjoq

by Xingqian Xu, Mang Tik Chiu, Thomas S. Huang, Honghui Shi

Released as a article .

2020  

Abstract

Most of the modern instance segmentation approaches fall into two categories: region-based approaches in which object bounding boxes are detected first and later used in cropping and segmenting instances; and keypoint-based approaches in which individual instances are represented by a set of keypoints followed by a dense pixel clustering around those keypoints. Despite the maturity of these two paradigms, we would like to report an alternative affinity-based paradigm where instances are segmented based on densely predicted affinities and graph partitioning algorithms. Such affinity-based approaches indicate that high-level graph features other than regions or keypoints can be directly applied in the instance segmentation task. In this work, we propose Deep Affinity Net, an effective affinity-based approach accompanied with a new graph partitioning algorithm Cascade-GAEC. Without bells and whistles, our end-to-end model results in 32.4% AP on Cityscapes val and 27.5% AP on test. It achieves the best single-shot result as well as the fastest running time among all affinity-based models. It also outperforms the region-based method Mask R-CNN.
In text/plain format

Archived Files and Locations

application/pdf  2.4 MB
file_rhpfauaptbf5vozvejtqov5iwi
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-03-15
Version   v1
Language   en ?
arXiv  2003.06849v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: eee99e5e-0a11-483f-81f6-cf9540e432f7
API URL: JSON