How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models

• URL: http://arxiv.org/abs/2601.22841v1
• Date: Fri, 30 Jan 2026 11:08:48 GMT
• Title: How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models
• Abstract summary: Large-scale foundation models (FMs) in remote sensing (RS) are developed based on the paradigms established in computer vision (CV) and have shown promise for various Earth observation applications.<n>We hypothesize that RS FMs enter an over parameterized regime at substantially smaller scales than their CV counterparts.<n>We use post-hoc slimming to measure representational redundancy across six state-of-the-art RS FMs on four downstream classification tasks.<n>Our findings establish post-hoc slimmability as both a practical deployment strategy for resource-constrained environments and a diagnostic tool that challenges the prevailing scaling paradigm in RS
• Score: 5.429166905724048
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large-scale foundation models (FMs) in remote sensing (RS) are developed based on the paradigms established in computer vision (CV) and have shown promise for various Earth observation applications. However, the direct transfer of scaling assumptions from CV to RS has not been adequately examined. We hypothesize that RS FMs enter an overparameterized regime at substantially smaller scales than their CV counterparts, where increasing parameter count primarily induces redundant representations rather than qualitatively new abstractions. To test this hypothesis, we use post-hoc slimming, where we uniformly reduce the width of pretrained encoder, as a tool to measure representational redundancy across six state-of-the-art RS FMs on four downstream classification tasks. Our findings reveal a significant contrast with those in the CV domain: while a post-hoc slimmed masked autoencoder (MAE) trained on ImageNet retains less than 10% accuracy at 1% FLOPs, RS FMs maintain over 71% relative accuracy at the same budget. This sevenfold difference provides strong empirical support for our hypothesis. We further demonstrate that learned slimmable training can improve both Momentum Contrast (MoCo)- and MAE- based models. In addition, through the explained variance ratio and the feature correlation analysis, we provide mechanistic explanations showing that RS FMs distribute task-relevant information with high redundancy. Our findings establish post-hoc slimmability as both a practical deployment strategy for resource-constrained environments and a diagnostic tool that challenges the prevailing scaling paradigm in RS. Upon acceptance, we will publish all code.

Related papers

• Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory [77.27772368491698]
  Spectrals such as Muon have recently shown strong empirical performance in large-scale language model training.<n>We study this question through the linear associative memory problem.<n>We show that the storage capacity of Muon significantly exceeds that of SGD.
  arXiv  Detail & Related papers  (2026-03-27T16:13:18Z)
• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Beyond Weight Adaptation: Feature-Space Domain Injection for Cross-Modal Ship Re-Identification [3.6907522136316975]
  Cross-Modality Ship Re-Identification (CMS Re-ID) is critical for achieving all-day and all-weather maritime target tracking.<n>We explore the potential of Vision Foundation Models (VFMs) in bridging modality gaps.<n>We propose a novel PEFT strategy termed Domain Representation Injection (DRI)
  arXiv  Detail & Related papers  (2025-12-24T02:30:23Z)
• PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection [9.241842285556134]
  PeftCD is a change detection framework built upon Vision Foundation Models.<n>It employs a weight-sharing encoder derived from a VFM, into which LoRA and Adapter modules are seamlessly integrated.<n>It achieves state-of-the-art performance across multiple public datasets.
  arXiv  Detail & Related papers  (2025-09-11T16:08:43Z)
• QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution [53.13952833016505]
  We propose a low-bit quantization model for real-world video super-resolution (VSR)<n>We use a calibration dataset to measure both spatial and temporal complexity for each layer.<n>We refine the FP and low-bit branches to achieve simultaneous optimization.
  arXiv  Detail & Related papers  (2025-08-06T14:35:59Z)
• Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts [79.18608192761512]
  Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable.<n>We propose a Few-Shot Prototypical Concept Classification framework that mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment.<n>Our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.
  arXiv  Detail & Related papers  (2025-06-05T06:39:43Z)
• DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
  We propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder.<n>DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
  arXiv  Detail & Related papers  (2024-05-24T05:46:04Z)
• Learning Optimal Features via Partial Invariance [18.552839725370383]
  Invariant Risk Minimization (IRM) is a popular framework that aims to learn robust models from multiple environments. We show that IRM can over-constrain the predictor and to remedy this, we propose a relaxation via $textitpartial invariance$. Several experiments, conducted both in linear settings as well as with deep neural networks on tasks over both language and image data, allow us to verify our conclusions.
  arXiv  Detail & Related papers  (2023-01-28T02:48:14Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)
• Voxelmorph++ Going beyond the cranial vault with keypoint supervision and multi-channel instance optimisation [8.88841928746097]
  Recent Learn2Reg benchmark shows single-scale U-Net architectures fall short of state-of-the-art performance for abdominal or intra-patient lung registration. Here, we propose two straightforward steps that greatly reduce this gap in accuracy. First, we employ keypoint self-supervision with a novel network head that predicts a discretised heatmap. Second, we replace multiple learned fine-tuning steps by a single instance with hand-crafted features and the Adam optimiser.
  arXiv  Detail & Related papers  (2022-02-28T19:23:29Z)
• Boosting Randomized Smoothing with Variance Reduced Classifiers [4.110108749051657]
  We motivate why ensembles are a particularly suitable choice as base models for Randomized Smoothing (RS) We empirically confirm this choice, obtaining state of the art results in multiple settings.
  arXiv  Detail & Related papers  (2021-06-13T08:40:27Z)
• Feature Quantization Improves GAN Training [126.02828112121874]
  Feature Quantization (FQ) for the discriminator embeds both true and fake data samples into a shared discrete space. Our method can be easily plugged into existing GAN models, with little computational overhead in training.
  arXiv  Detail & Related papers  (2020-04-05T04:06:50Z)

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.