Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement
This work addresses segmentation for ultra-high resolution images, which is important for realistic applications, but appears incremental as it builds on existing patch-based pipelines.
The paper tackles ultra-high resolution image segmentation by introducing a locality-aware context fusion model and alternating local enhancement module, achieving state-of-the-art performance on public benchmarks.
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. Our released codes are available at: https://github.com/liqiokkk/FCtL.