AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Training and Inference Within 1 Second – Tackle Cross-Sensor Degradation of Real-World Pansharpening with Efficient Residual Feature Tailoring

Tianyu Xin, Jin-Liang Xiao, Zeyu Xia, Shan Yin, Liang-Jian Deng

AAAI 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 2 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 Feature Tailor module (ablation)FusionNet with patch-wise strategy · WV-3 -> WV-2HQNR: 0.8395 -> 0.8970Improved
add Feature Tailor module (ablation)U2Net with patch-wise strategy · WV-3 -> WV-2HQNR: 0.7088 -> 0.8264Improved
add patch-wise training and inference (ablation)U2Net with Feature Tailor · WV-3 -> WV-2Duration (s): 7.53 -> 0.89Improved
add patch-wise training and inference (ablation)FusionNet with Feature Tailor · WV-3 -> WV-2Duration (s): 0.45 -> 0.13Improved
add patch-wise training and inference (ablation)FusionNet with Feature Tailor · WV-3 -> WV-2HQNR: 0.9002 -> 0.8970Mixed
add patch-wise training and inference (ablation)U2Net with Feature Tailor · WV-3 -> WV-2HQNR: 0.8308 -> 0.8264Hurt
insert Feature Tailor before channel mapper instead of after (pre-CM vs post-CM) (ablation)ERFT on FusionNet and U2Net · WV3 (HQNR)HQNRImproved
add ERFT to pretrained FusionNetFusionNet · QB -> GF-2HQNR: 0.8397 -> 0.8970Improved
add ERFT to pretrained U2NetU2Net · QB -> GF-2HQNR: 0.7089 -> 0.8264Improved
add ERFT to pretrained U2NetU2Net · WV-3 -> WV-2HQNR: 0.8706 -> 0.9128Improved
use ERFT-U2Net instead of zero-shot ZS-PanU2Net · QB -> GF-2HQNR: 0.8925 -> 0.8264Hurt
use ERFT-FusionNet instead of zero-shot ZS-PanFusionNet · QB -> GF-2 / WV-3 -> WV-2Duration (s): 66.74 -> 0.11 (QB to GF-2)Improved

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