Research map / Detection and segmentation / CNN features
From Contexts to Locality: Ultra-High Resolution Image Segmentation via Locality-Aware Contextual Correlation
Qi Li, Weixiang Yang, Wenxi Liu, Yuanlong Yu, Shengfeng He
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add local, medium and large contexts (ablation) | FCN-8s baseline · DeepGlobe | mIOU (%): 71.84 -> 73.22 | Improved |
| add local, medium and large contexts (ablation) | FCN-8s baseline · Inria Aerial | mIOU (%): 69.08 -> 73.53 | Improved |
| use medium or large context alone instead of local context (ablation) | context model · Inria Aerial | mIOU (%): 72.50 -> 72.48 | Hurt |
| combine all three contexts instead of one (ablation) | context model · DeepGlobe | mIOU (%): 72.67 -> 73.22 | Improved |
| use locality-aware contextual correlation instead of feature concatenation (ablation) | context model · DeepGlobe | mIOU (%): 72.2 -> 73.5 | Improved |
| use locality-aware contextual correlation instead of feature concatenation (ablation) | context model · Inria Aerial | mIOU (%): 72.8 -> 73.7 | Improved |
| use adaptive fusion instead of averaging fusion (ablation) | context model · DeepGlobe | mIOU (%): 72.67 -> 73.22 | Improved |
| use adaptive fusion instead of weighted fusion (ablation) | context model · Inria Aerial | mIOU (%): 73.43 -> 73.53 | Improved |
| add contextual semantics refinement network instead of montaging (ablation) | full model · DeepGlobe | mIOU (%): 73.22 -> 73.45 | Improved |
| choose refinement context size 1016 instead of 762 (ablation) | refinement network · DeepGlobe | mIOU (%): 73.24 -> 73.45 | Improved |
| add refinement network to GLNet | GLNet · DeepGlobe | mIOU (%): 71.6 -> 72.6 | Improved |
| use whole image as large context (2448) instead of 2032 (ablation) | context size · DeepGlobe | mIOU (%): 71.97 -> 73.22 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ICNet — ICNet: Intra-saliency Correlation Network for Co-Saliency Detection (NeurIPS 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Ultra-High Resolution Image Segmentation via Locality-Aware Context Fusion and Alternating Local Enhancement (IJCV 2024 · similarity 0.95)
- Ultra-High Resolution Segmentation via Boundary-Enhanced Patch-Merging Transformer (AAAI 2025 · similarity 0.88)
- Toward Real Ultra Image Segmentation: Leveraging Surrounding Context to Cultivate General Segmentation Model (NeurIPS 2024 · similarity 0.88)
- CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement (CVPR 2020 · similarity 0.87)
- Semantic Correlation Promoted Shape-Variant Context for Segmentation (CVPR 2019 · similarity 0.87)
- Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
