From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation
Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resolution image segmentation pipeline, in which an ultrahigh resolution image is partitioned into regular patches for local seg...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8531 https://ink.library.smu.edu.sg/context/sis_research/article/9534/viewcontent/From_Contexts_to_Locality__Ultra_High_Resolution_Image_Segmentation_via_Locality_Aware_Contextual_Correlation.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9534 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-95342024-01-22T14:58:40Z From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation LI, Qi YANG, Weixiang LIU, Wenxi YU, Yuanlong HE, Shengfeng Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resolution image segmentation pipeline, in which an ultrahigh resolution image is partitioned into regular patches for local segmentation and then the local results are merged into a high-resolution semantic mask. In particular, we introduce a novel locality-aware contextual correlation based segmentation model to process local patches, where the relevance between local patch and its various contexts are jointly and complementarily utilized to handle the semantic regions with large variations. Additionally, we present a contextual semantics refinement network that associates the local segmentation result with its contextual semantics, and thus is endowed with the ability of reducing boundary artifacts and refining mask contours during the generation of final high-resolution mask. Furthermore, in comprehensive experiments, we demonstrate that our model outperforms other state-of-the-art methods in public benchmarks. 2021-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8531 info:doi/10.1109/ICCV48922.2021.00716 https://ink.library.smu.edu.sg/context/sis_research/article/9534/viewcontent/From_Contexts_to_Locality__Ultra_High_Resolution_Image_Segmentation_via_Locality_Aware_Contextual_Correlation.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Contextual semantics High resolution High resolution image segmentation Locality aware Realistic applications Resolution images Segmentation models Segmentation results Semantic refinement Ultra high resolution Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Contextual semantics High resolution High resolution image segmentation Locality aware Realistic applications Resolution images Segmentation models Segmentation results Semantic refinement Ultra high resolution Databases and Information Systems |
spellingShingle |
Contextual semantics High resolution High resolution image segmentation Locality aware Realistic applications Resolution images Segmentation models Segmentation results Semantic refinement Ultra high resolution Databases and Information Systems LI, Qi YANG, Weixiang LIU, Wenxi YU, Yuanlong HE, Shengfeng From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation |
description |
Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resolution image segmentation pipeline, in which an ultrahigh resolution image is partitioned into regular patches for local segmentation and then the local results are merged into a high-resolution semantic mask. In particular, we introduce a novel locality-aware contextual correlation based segmentation model to process local patches, where the relevance between local patch and its various contexts are jointly and complementarily utilized to handle the semantic regions with large variations. Additionally, we present a contextual semantics refinement network that associates the local segmentation result with its contextual semantics, and thus is endowed with the ability of reducing boundary artifacts and refining mask contours during the generation of final high-resolution mask. Furthermore, in comprehensive experiments, we demonstrate that our model outperforms other state-of-the-art methods in public benchmarks. |
format |
text |
author |
LI, Qi YANG, Weixiang LIU, Wenxi YU, Yuanlong HE, Shengfeng |
author_facet |
LI, Qi YANG, Weixiang LIU, Wenxi YU, Yuanlong HE, Shengfeng |
author_sort |
LI, Qi |
title |
From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation |
title_short |
From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation |
title_full |
From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation |
title_fullStr |
From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation |
title_full_unstemmed |
From contexts to locality: Ultra-high resolution image segmentation via locality-aware contextual correlation |
title_sort |
from contexts to locality: ultra-high resolution image segmentation via locality-aware contextual correlation |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2021 |
url |
https://ink.library.smu.edu.sg/sis_research/8531 https://ink.library.smu.edu.sg/context/sis_research/article/9534/viewcontent/From_Contexts_to_Locality__Ultra_High_Resolution_Image_Segmentation_via_Locality_Aware_Contextual_Correlation.pdf |
_version_ |
1789483259969667072 |