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

• URL: http://arxiv.org/abs/2603.19873v1
• Date: Fri, 20 Mar 2026 11:38:32 GMT
• Title: SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation
• Abstract summary: We introduce SIMPLER, a pre-fine-tuning architecture selection method that reduces inference and deployment costs.<n>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.
• Score: 3.1313965020437546
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Scalable Hyperparameter-Divergent Ensemble Training with Automatic Learning Rate Exploration for Large Models [8.687019807776881]
  Training large neural networks with data-parallel gradient descent allocates N GPU replicas to compute effectively identical updates.<n>We propose a method that repurposes these replicas for simultaneous learning rate configurations overhead.<n>We further propose an automatic learning rate (autoLR) controller that treats the relative training loss across replicas as a performance signal.
  arXiv  Detail & Related papers  (2026-04-27T17:17:28Z)
• GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning [24.48876360953984]
  Layer-wise fine-tuning methods have emerged as an alternative, enabling memory-efficient training.<n>We propose a gradient-based adaptive layer-wise importance sampling framework.<n>We consistently outperforms state-of-the-art methods, achieving an average accuracy improvement of up to 4.38 points and reducing memory usage by up to 19.97%.
  arXiv  Detail & Related papers  (2026-04-09T05:04:37Z)
• Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning [71.30276778807068]
  We propose a unified framework that strategically coordinates sample pruning and token pruning.<n>Q-Tuning achieves a +38% average improvement over the full-data SFT baseline using only 12.5% of the original training data.
  arXiv  Detail & Related papers  (2025-09-28T13:27:38Z)
• Analysis of Hyperparameter Optimization Effects on Lightweight Deep Models for Real-Time Image Classification [0.0]
  This study evaluates the accuracy and deployment feasibility of seven modern lightweight architectures: ConvNeXt-T, EfficientV2-S, MobileNetV3-L, MobileViT v2 (S/XS), RepVGG-A2, and TinyViT-21M.<n> tuning alone leads to a top-1 accuracy improvement of 1.5 to 3.5 percent over baselines, and select models deliver latency under 5 milliseconds and over 9,800 frames per second.
  arXiv  Detail & Related papers  (2025-07-31T07:47:30Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Time-, Memory- and Parameter-Efficient Visual Adaptation [75.28557015773217]
  We propose an adaptation method which does not backpropagate gradients through the backbone. We achieve this by designing a lightweight network in parallel that operates on features from the frozen, pretrained backbone.
  arXiv  Detail & Related papers  (2024-02-05T10:55:47Z)
• Hierarchical Side-Tuning for Vision Transformers [33.536948382414316]
  Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. PETL has shown potential for achieving high performance with fewer parameter updates compared to full fine-tuning. This paper introduces Hierarchical Side-Tuning (HST), an innovative PETL method facilitating the transfer of ViT models to diverse downstream tasks.
  arXiv  Detail & Related papers  (2023-10-09T04:16:35Z)
• Prompt Tuning for Parameter-efficient Medical Image Segmentation [79.09285179181225]
  We propose and investigate several contributions to achieve a parameter-efficient but effective adaptation for semantic segmentation on two medical imaging datasets. We pre-train this architecture with a dedicated dense self-supervision scheme based on assignments to online generated prototypes. We demonstrate that the resulting neural network model is able to attenuate the gap between fully fine-tuned and parameter-efficiently adapted models.
  arXiv  Detail & Related papers  (2022-11-16T21:55:05Z)
• Online Convolutional Re-parameterization [51.97831675242173]
  We present online convolutional re- parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks.
  arXiv  Detail & Related papers  (2022-04-02T09:50:19Z)
• Layer Pruning on Demand with Intermediate CTC [50.509073206630994]
  We present a training and pruning method for ASR based on the connectionist temporal classification (CTC) We show that a Transformer-CTC model can be pruned in various depth on demand, improving real-time factor from 0.005 to 0.002 on GPU.
  arXiv  Detail & Related papers  (2021-06-17T02:40:18Z)
• Layer Reduction: Accelerating Conformer-Based Self-Supervised Model via Layer Consistency [31.572652956170252]
  Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. We experimentally achieve 7.8X parameter reduction, 41.9% training speedup and 37.7% inference speedup while maintaining comparable performance with conventional BERT-like self-supervised methods.
  arXiv  Detail & Related papers  (2021-04-08T08:21:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.