AI Paper Atlas

Research map / Detection and segmentation / CNN features

CRISP: Calibration-Aware Visual State Space Duality for Remote Sensing Image Segmentation

kangning wang, Haopeng Zhang, Zhiguo Jiang

ECCV 2026 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation

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 residual injection (ablation)VSSD+UPerHead · Potsdam val (single-scale)mIoU: 87.32 -> 87.65Improved
add high-pass modulation (ablation)VSSD+UPerHead · Potsdam val (single-scale)mIoU: 87.32 -> 87.68Improved
add DC/HC rebalancing (ablation)VSSD+UPerHead · Potsdam val (single-scale)mIoU: 87.32 -> 87.64Improved
add residual injection to Hi-Pass + DC/HC (ablation)DCO · Potsdam val (single-scale)mIoU: 87.83 -> 88.10Improved
add full DCO (ablation)VSSD+UPerHead · Potsdam val (single-scale)mIoU: 87.32 -> 88.10Improved
add OMP head without DCO (ablation)VSSD · Potsdam val (single-scale)mIoU: 87.32 -> 85.63Hurt
add OMP head on top of DCO without regularizers (ablation)DCO · Potsdam val (single-scale)mIoU: 88.10 -> 86.85Hurt
add orthogonality loss to DCO+OMP (ablation)DCO+OMP · Potsdam val (single-scale)mIoU: 86.85 -> 88.06Improved
add margin loss to DCO+OMP (ablation)DCO+OMP · Potsdam val (single-scale)mIoU: 86.85 -> 88.02Improved
add both regularizers to DCO+OMP (ablation)DCO+OMP · Potsdam val (single-scale)mIoU: 86.85 -> 88.25Improved
replace UPerHead with OMP head (with DCO and both regularizers) (ablation)DCO · Potsdam val (single-scale)mIoU: 88.10 -> 88.25Improved
increase prototypes K from 3 to larger (ablation)OMP · Potsdam val (single-scale)mIoUNo clear effect

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