AI Paper Atlas

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

On the Generalization of Representation Uncertainty in Earth Observation

Spyros Kondylatos, Nikolaos Ioannis Bountos, Dimitrios Michail, Xiao Xiang Zhu, Gustau Camps-Valls, Ioannis Papoutsis

ICCV 2025 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 4 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
pretrain the uncertainty module on EO data instead of ImageNetViT uncertainty module · EO inference datasetsLA-CPA / R-CPAImproved
use ImageNet-pretrained uncertainty module on EO dataViT uncertainty module · EO inference datasetsLA-CPAHurt
coarser pretraining targets (BigEarthNet-5 instead of BigEarthNet) (ablation)ViT-Tiny and ViT-Small · EO inference datasetsLA-CPAImproved
coarser pretraining targets (BigEarthNet-5 instead of BigEarthNet) (ablation)ViT-Base and ViT-Large · EO inference datasetsLA-CPANo clear effect
pretrain at original 120x120 resolution rather than downscaled (ablation)ViT-Large on BigEarthNet · MLRSNet, Woody, Waititu, FlairLA-CPAImproved
downscale pretraining resolution to 60x60 or 30x30 (ablation)ViT-Large on BigEarthNet · BigEarthNet, MARIDALA-CPANo clear effect
downscale pretraining resolution to 16x16 (ablation)ViT-Large on BigEarthNet · all datasetsLA-CPAHurt
pretrain on Flair rather than BigEarthNetViT uncertainty module · Woody and WaitituLA-CPAImproved
use max pixel loss instead of mean pixel loss in discard test (ablation)EO-pretrained uncertainty · Flair discard testdownstream loss trendImproved
EO-pretrained (Flair) vs ImageNet uncertainty on noisy BigEarthNetViT variants · noisy vs noise-free BigEarthNetpredicted uncertaintyImproved
use SAR instead of RGB inputBigEarthNet-pretrained ViT · BigEarthNetLA@1Hurt
use SAR instead of RGB inputViT-Base and ViT-Large · BigEarthNetLA-CPAMixed

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