DARN: Dynamic Adaptive Regularization Networks for Efficient and Robust Foundation Model Adaptation
Foundation models (FMs) offer powerful representations for geospatial analysis, but adapting them effectively remains challenging. Standard adaptation methods, whether full fine-tuning or efficient frozen-backbone approaches, typically employ decoders with fixed regularization strategies, failing to account for the significant heterogeneity in satellite imagery. We introduce Dynamic Adaptive Regularization Networks (DARN), a novel decoder architecture designed to address this limitation. DARN integrates three key innovations: (1) a lightweight Task Complexity Predictor (TCP) that estimates per-sample difficulty, (2) Adaptive Dropout Modulation (ADM), dynamically adjusting dropout rates (from 0.1 to 0.5) based on predicted complexity, and (3) Dynamic Capacity Gating (DCG) that modulates channel activation. We provide theoretical justifications linking DARN's optimization to stationary point convergence and its mechanism to adaptive information bottlenecks. Empirically, DARN demonstrates exceptional performance across both major adaptation paradigms. In full fine-tuning (unfrozen backbone), DARN achieves a new state-of-the-art on the multi-task GeoBench benchmark (86.66% mIoU, +5.56 pp over prior SOTA). In efficient adaptation (frozen backbone), DARN achieves SOTA-competitive accuracy (90.5% mIoU on Sen1Floods11) while delivering substantial advantages crucial for real-world deployment: superior out-of-distribution (OOD) generalization (+9.5 pp mIoU on AI4SmallFarms), enhanced robustness (17% relative reduction in corruption error), and improved performance on minority classes. DARN offers a more intelligent, robust, and efficient approach to leveraging FMs in critical geospatial applications.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling
Genomic foundation models increasingly adopt large language model architectures, yet almost universally rely on fixed tokenization schemes such as $k$-mers, BPE, or single nucleotides, which impose arbitrary sequence bou…
DARNet: Bridging Domain Gaps in Cross-Domain Few-Shot Segmentation with Dynamic Adaptation
Few-shot segmentation (FSS) aims to segment novel classes in a query image by using only a small number of supporting images from base classes. However, in cross-domain few-shot segmentation (CD-FSS), leveraging features…
Cross-Domain Few-ShotSegmentationSpecificityTest-time AdaptationAdaRNN: Adaptive Learning and Forecasting of Time Series
Time series has wide applications in the real world and is known to be difficult to forecast. Since its statistical properties change over time, its distribution also changes temporally, which will cause severe distribut…
Activity RecognitionFinancial AnalysisHuman Activity RecognitionTime Series+1ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs
Conventional Low-Rank Adaptation (LoRA) methods employ a fixed rank, imposing uniform adaptation across transformer layers and attention heads despite their heterogeneous learning dynamics. This paper introduces Adaptive…
parameter-efficient fine-tuningLiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation
We present a boundary-aware domain adaptation model for LiDAR scan full-scene semantic segmentation (LiDARNet). Our model can extract both the domain private features and the domain shared features with a two-branch stru…
DiversityDomain AdaptationSegmentationSemantic Segmentation