Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model

• URL: http://arxiv.org/abs/2606.12218v1
• Date: Wed, 10 Jun 2026 15:31:37 GMT
• Title: Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model
• Abstract summary: Prithvi-EO has shown strong transferability across computer vision tasks.<n>It produces features at a single spatial scale that are ill-suited for the multi-scale features required by object detection heads.<n>We show that lightweight spatial prior fusion and selective backbone unfreezing enable Prithvi-EO to capture local fallow patterns more effectively.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding spatial distribution of fallow land is important for optimizing the food-water (FW) nexus, given fallowing's role in crop rotation and water conservation. Fallow is a low accuracy class in USDA Cropland Data Layer (CDL). Geospatial foundation model (GFM), Prithvi-EO has shown strong transferability across computer vision tasks. However, its Vision Transformer (ViT) backbone produces features at a single spatial scale that are ill-suited for the multi-scale features required by object detection heads. Existing approaches synthesise multi-scale pyramids through scaling of single stride tokens, sacrificing spatial heterogeneity, and full backbone fine-tuning is computationally prohibitive for GFMs. We evaluate a fallow detection pipeline combining two parameter-efficient fine tuning (PEFT) schemes: Low-Rank Adaptation (LoRA) and a hybrid PEFT, with three neck designs: pseudo multi-scale, Lite ViT-Adapter, and Full ViT-Adapter. Our best configuration, Lite ViT-Adapter with a one-stage head, achieves a mAP@50 of 0.9479 with the Diou loss, suggesting the effectiveness of center-aware localization for irregular fallow field detection. ViT-Adapter free one-stage detection under LoRA improves the adapter-free anchor-based approach by 6.42%, and the best configuration improves baseline adapter-free anchor-based approach by 25.70%. These results demonstrate that lightweight spatial prior fusion and selective backbone unfreezing enable Prithvi-EO to capture local fallow patterns more effectively, outperforming approaches that rely on reshaped single-stride ViT tokens.

Related papers

• DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images [50.96240625673857]
  DroneFINE is a novel PEFT paradigm comprising two domain-aware complementary modules tailored for VLM-based drone image detectors.<n>DroneFINE significantly outperforms existing PEFT methods and achieves performance comparable to full fine-tuning.
  arXiv  Detail & Related papers  (2026-07-01T02:27:40Z)
• TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimation [14.854437007037683]
  Monoattention 6-F spacecraft pose estimation methods process individual frames, discarding the temporal information present in an image sequence acquired during manoeuvres.<n>We propose TALON (Token-conditioned adapters): 3D adapters injected before self-tuning layers of a frozen ViT vision transformer.<n>Pre-Aligned allows the frozen attention to reason over temporally enriched tokens, achieving stronger performance with a single adapter per block than post-attention alternatives.<n>On SPADES dataset, TA reduces the pose error by 50% over the prior state-of-the-art, and on Swiss dataset it surpasses the prior best by 21.8% in ADD-0.1d
  arXiv  Detail & Related papers  (2026-05-29T12:21:52Z)
• FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales [65.4821703903285]
  FLORO is a multimodal foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus.<n> FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data.<n>We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks.
  arXiv  Detail & Related papers  (2026-05-27T08:55:54Z)
• PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection [73.05827565991488]
  PKINet-v2 synergizes anisotropic axial-strip convolutions with isotropic square kernels and builds a multi-scope receptive field.<n>PKINet-v2 achieves state-of-the-art accuracy while delivering a $bf3.9times$ FPS acceleration compared to PKINet-v1.
  arXiv  Detail & Related papers  (2026-03-17T10:17:58Z)
• StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimation [18.410248448681514]
  We propose StereoAdapter-2, which replaces the conventional ConvGRU updater with a novel ConvSS2D operator.<n>We construct UW-StereoDepth-80K, a large-scale synthetic underwater stereo dataset.<n>Our framework achieves state-of-the-art zero-shot performance on underwater benchmarks.
  arXiv  Detail & Related papers  (2026-02-18T22:12:08Z)
• LC4-DViT: Land-cover Creation for Land-cover Classification with Deformable Vision Transformer [14.684808109822386]
  LC4-DViT is a framework that combines generative data creation with a deformation-aware Vision Transformer.<n>A text-guided diffusion pipeline uses GPT-4o-generated scene descriptions to synthesize high-fidelity training images.<n>DViT couples a DCNv4 deformable convolutional backbone with a Vision Transformer encoder to jointly capture fine-scale geometry and global context.
  arXiv  Detail & Related papers  (2025-11-27T23:56:35Z)
• MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection [54.545054873239295]
  Deepfakes have recently raised significant trust issues and security concerns among the public.<n>ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance.<n>This work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach.
  arXiv  Detail & Related papers  (2024-04-12T13:02:08Z)
• D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition [64.153799533257]
  D$2$ST-Adapter is structured with an internal dual-pathway architecture that enables built-in disentangled encoding of spatial and temporal features.<n>Our method is particularly well-suited to challenging scenarios where temporal dynamics are critical for action recognition.
  arXiv  Detail & Related papers  (2023-12-03T15:40:10Z)
• Efficient Decoder-free Object Detection with Transformers [75.00499377197475]
  Vision transformers (ViTs) are changing the landscape of object detection approaches. We propose a decoder-free fully transformer-based (DFFT) object detector. DFFT_SMALL achieves high efficiency in both training and inference stages.
  arXiv  Detail & Related papers  (2022-06-14T13:22:19Z)
• Vision Transformer Adapter for Dense Predictions [57.590511173416445]
  Vision Transformer (ViT) achieves inferior performance on dense prediction tasks due to lacking prior information of images. We propose a Vision Transformer Adapter (ViT-Adapter) which can remedy the defects of ViT and achieve comparable performance to vision-specific models. We verify the effectiveness of our ViT-Adapter on multiple downstream tasks, including object detection, instance segmentation, and semantic segmentation.
  arXiv  Detail & Related papers  (2022-05-17T17:59:11Z)

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.