AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation

Tingzhang Luo, Ruizhong Liu, Yichao Liu, Cheng Fan, Yu Liu, Jianyuan Guo

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 1 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 Cascaded Representation Extraction (CRE) distilling SAM geometry into multiple SigLIP layers (ablation)SigLIP 2 + SAM 2 baseline · RefSegRS testcIoU: 80.82 -> 82.55Improved
add Text-Guided Relational Distillation (TGD) on top of CRE (ablation)CROSS · RefSegRS testcIoU: 82.55 -> 83.15Improved
add PSCL on top of LGCD (ablation)CROSS · RRSIS-D testcIoU: 79.02 -> 79.89Improved
add PSCL on top of LGCD (ablation)CROSS · RefSegRS testcIoU: 83.15 -> 83.25Improved
add PSCL alone to baseline (ablation)SigLIP 2 + SAM 2 baseline · RefSegRS testcIoU: 80.82 -> 82.11Improved
use spatial counterfactual negatives only (no perspective negatives) (ablation)PSCL · RRSIS-D testcIoU: 79.02 -> 78.70Hurt
add perspective hard negatives to PSCL (ablation)PSCL · RRSIS-D testcIoU: 79.02 -> 79.34Improved
add spatial counterfactual negatives on RefSegRS (ablation)PSCL · RefSegRS testcIoU: 83.15 -> 83.20No clear effect
choose distillation layers {5,15,27} instead of {9,18,27} (ablation)CROSS · RefSegRS testcIoU: 83.25 -> 82.76Hurt
replace Qwen2.5-7B counterfactual generator with GPT-4o or Llama-3.1-8B (ablation)PSCL · RRSIS-D testcIoU: 79.89 -> 79.86 (GPT-4o), 79.84 (Llama)No clear effect
CROSS vs RSRefSeg-2 on RRSIS-DCROSS · RRSIS-D testgIoU: 69.17 -> 68.92Mixed
CROSS vs RSRefSeg-2 on RefSegRSCROSS · RefSegRS testPr@0.9: 34.40 -> 41.32Improved

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