通过相似性筛选层，大幅减少遥感模型训练与推理开销。
SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation
- 用无梯度的层间相似性判断冗余层，预剪枝选深度。
- 在普里蒂维-EO-2上砍掉79%参数，性能保留94%，训练提速2.1倍。
- 无需调参，适配多模态、多架构遥感模型，适合资源受限场景。
为遥感任务微调基础模型成本高昂，训练和部署均需大量算力。现有参数高效方法降低训练成本但保留完整推理复杂度，后处理压缩则需先完成昂贵的全量微调。本文提出SIMPLER，一种微调前的架构选择方法：利用预训练视觉变换器深层表征的稳定性，计算未标注任务数据上各层表示的相似性，通过自动化评分函数识别冗余层，全程无需梯度、幅度启发或超参调优。在Prithvi-EO-2上，SIMPLER可裁剪最高79%参数，性能保持94%，实现2.1倍训练加速与2.6倍推理加速。该方法推广至TerraMind（多模态遥感基础模型）和ImageNet预训练的ViT-MAE，在不同任务、架构与光谱模态下均有效。代码已开源于https://gitlab.citius.gal/hpc4rs/simpler。
原文摘要 · Abstract (English)
Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and deployment. Parameter-efficient methods reduce training cost but retain full inference complexity, while post-hoc compression optimizes inference only after costly full fine-tuning. We introduce SIMPLER, a pre-fine-tuning architecture selection method that reduces inference and deployment costs by identifying an effective model depth before adaptation. SIMPLER exploits stabilization of representations in deeper layers of pre-trained vision transformers: it computes layer-wise representation similarity on unlabeled task data and applies an automated scoring function to select redundant layers, with no gradients, magnitude heuristics, or hyperparameter tuning required. On Prithvi-EO-2, SIMPLER prunes up to 79% of parameters while retaining 94% of baseline performance, yielding a 2.1x training speedup and 2.6x inference speedup. The method generalizes to TerraMind (a multimodal EO foundation model) and ImageNet-pretrained ViT-MAE, demonstrating applicability across tasks, architectures, and spectral modalities. Code is available at https://gitlab.citius.gal/hpc4rs/simpler.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。