AI Paper Atlas

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

ICCV 2021 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 71 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 -> 73.22Improved
add local, medium and large contexts (ablation)FCN-8s baseline · Inria AerialmIOU (%): 69.08 -> 73.53Improved
use medium or large context alone instead of local context (ablation)context model · Inria AerialmIOU (%): 72.50 -> 72.48Hurt
combine all three contexts instead of one (ablation)context model · DeepGlobemIOU (%): 72.67 -> 73.22Improved
use locality-aware contextual correlation instead of feature concatenation (ablation)context model · DeepGlobemIOU (%): 72.2 -> 73.5Improved
use locality-aware contextual correlation instead of feature concatenation (ablation)context model · Inria AerialmIOU (%): 72.8 -> 73.7Improved
use adaptive fusion instead of averaging fusion (ablation)context model · DeepGlobemIOU (%): 72.67 -> 73.22Improved
use adaptive fusion instead of weighted fusion (ablation)context model · Inria AerialmIOU (%): 73.43 -> 73.53Improved
add contextual semantics refinement network instead of montaging (ablation)full model · DeepGlobemIOU (%): 73.22 -> 73.45Improved
choose refinement context size 1016 instead of 762 (ablation)refinement network · DeepGlobemIOU (%): 73.24 -> 73.45Improved
add refinement network to GLNetGLNet · DeepGlobemIOU (%): 71.6 -> 72.6Improved
use whole image as large context (2448) instead of 2032 (ablation)context size · DeepGlobemIOU (%): 71.97 -> 73.22Improved

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