AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation

Víctor Barreiro, Johannes Jakubik, Francisco Argüello, Dora Heras

ECCV 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 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
use CKA instead of Jaccard/SVCCA for layer selection (ablation)SIMPLER · MADOSmIoU: 50.7 -> 62.8Improved
add ImageNet-style pre-training (Prithvi) versus from scratch (ablation)SIMPLER 5-block · MADOSmIoU: 44.1 -> 62.8Improved
add pre-training to full baseline (ablation)Prithvi-EO-2 300M · MADOSmIoU: 46.7 -> 66.9Improved
prune 5-block depth instead of full 24 blocks, from scratch (ablation)Prithvi-EO-2 300M · MADOS (from scratch)mIoU: 44.1 vs 46.7No clear effect
select depth with SIMPLER instead of 40% magnitude pruningPrithvi-EO-2 300M · MADOSmIoU: 47.9 -> 62.8Improved
increase CKA samples from 10 to 500 (ablation)SIMPLER · MADOScutoff std (blocks): 2.95 -> 0.53Improved
increase CKA samples from 500 to 1000 (ablation)SIMPLER · MADOScomputation time: 218s -> 678sHurt
apply SIMPLER to TerraMind-SmallTerraMind-Small · MADOS (TerraMind)mIoU: 53.0 -> 53.6Improved
apply SIMPLER to TerraMind-LargeTerraMind-Large · MADOS (TerraMind)mIoU: 70.1 -> 58.8Hurt
apply SIMPLER to ViT-MAE on CIFAR-100ViT-MAE · CIFAR-100accuracy: 88.8 -> 72.8Hurt
apply SIMPLER to Prithvi-EO-2 300MPrithvi-EO-2 300M · BigEarthNetv2mAP: 73.4 -> 71.2Hurt
apply SIMPLER to Prithvi-EO-2 300MPrithvi-EO-2 300M · Sen4MapF1-macro: 66.6 -> 63.8Hurt

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