Publication Type

Journal Article

Version

publishedVersion

Publication Date

11-2024

Abstract

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 ultra-high 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 context fusion 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 the alternating local enhancement module that restricts the negative impact of redundant information introduced from the contexts, and thus is endowed with the ability of fixing the locality-aware features to produce refined results. Furthermore, in comprehensive experiments, we demonstrate that our model outperforms other state-of-the-art methods in public benchmarks and verify the effectiveness of the proposed modules.

Keywords

Attention mechanisms, Context-guided vision model, Geo-spatial, Geo-spatial image segmentation, High resolution image segmentation, Images segmentations, Spatial images, Ultra-high resolution image segmentation, Ultrahigh resolution, Vision model

Discipline

Artificial Intelligence and Robotics | Databases and Information Systems

Research Areas

Data Science and Engineering; Information Systems and Management

Publication

International Journal of Computer Vision

Volume

132

Issue

11

First Page

5030

Last Page

5047

ISSN

0920-5691

Identifier

10.1007/s11263-024-02045-3

Publisher

Springer

Additional URL

https://doi.org/10.1007/s11263-024-02045-3

Download

Share

COinS