AI Paper Atlas

Research map / Detection and segmentation / CNN features

Ultra-High Resolution Image Segmentation via Locality-Aware Context Fusion and Alternating Local Enhancement

Wenxi Liu, Qi Li, Xindai Lin, Weixiang Yang, Shengfeng He, Yuanlong Yu

IJCV 2024 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 28 citations (OpenAlex)

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 changedWhereMeasuredEffect
add local, medium and large contexts (ablation)FCN-8s baseline · DeepGlobemIoU: 71.84 -> 73.47Improved
add local, medium and large contexts (ablation)FCN-8s baseline · Inria AerialmIoU: 69.08 -> 73.50Improved
add gated positional embeddings (GPE) (ablation)three-context LCF · DeepGlobemIoU: 73.22 -> 73.47Improved
add gated positional embeddings (GPE) (ablation)three-context LCF · Inria AerialmIoU: 73.53 -> 73.50No clear effect
use medium or large context alone instead of local context (ablation)LCF · Inria AerialmIoU: 72.50 -> 72.48Hurt
use adaptive fusion instead of averaging (ablation)LCF · DeepGlobemIoU: 72.89 -> 73.47Improved
use adaptive fusion instead of averaging (ablation)LCF · Inria AerialmIoU: 73.20 -> 73.50Improved
use adaptive fusion instead of offline weighted fusion (ablation)LCF · DeepGlobemIoU: 73.16 -> 73.47Improved
replace ALE with feature concatenation (ablation)LCF · DeepGlobemIoU: 73.47 -> 72.20Hurt
add ALE to LCF (variant d) (ablation)LCF · DeepGlobemIoU: 73.47 -> 73.91Improved
add ALE to LCF (variant d) (ablation)LCF · Inria AerialmIoU: 73.50 -> 74.58Improved
use third-order instead of second-order ALE (ablation)LCF + ALE · DeepGlobemIoU: 73.91 -> 73.77Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy