paper-with-me

Papers

Compressing Vision Transformers in Geospatial Transfer Learning with Manifold-Constrained Optimization

2026-01-12 · Thomas Snyder, H. Lexie Yang, Stefan Schnake, Steffen Schotthöfer arxiv

Deploying geospatial foundation models on resource-constrained edge devices demands compact architectures that maintain high downstream performance. However, their large parameter counts and the accuracy loss often induced by compression limit practical adoption. In this work, we leverage manifold-constrained optimization framework DLRT to compress large vision transformer-based geospatial foundation models during transfer learning. By enforcing structured low-dimensional parameterizations aligned with downstream objectives, this approach achieves strong compression while preserving task-specific accuracy. We show that the method outperforms of-the-shelf low-rank methods as LoRA. Experiments on diverse geospatial benchmarks confirm substantial parameter reduction with minimal accuracy loss, enabling high-performing, on-device geospatial models.

📄 PDF Abstract BibTeX arXiv:2601.08882

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation

2021-07-03 · Zhiwei Hao, Jianyuan Guo, Ding Jia, Kai Han 외

In the past few years, transformers have achieved promising performances on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds their from being dep…

Knowledge DistillationModel CompressionTransfer Learning

MiniViT: Compressing Vision Transformers with Weight Multiplexing

2022-04-14 · CVPR 2022 1 · Jinnian Zhang, Houwen Peng, Kan Wu, Mengchen Liu 외

Vision Transformer (ViT) models have recently drawn much attention in computer vision due to their high model capability. However, ViT models suffer from huge number of parameters, restricting their applicability on devi…

DiversityImage Classification

GraphTransformers for Geospatial Forecasting of Hurricane Trajectories

2023-10-31 · Pallavi Banerjee, Satyaki Chakraborty

In this paper we introduce a novel framework for trajectory prediction of geospatial sequences using GraphTransformers. When viewed across several sequences, we observed that a graph structure automatically emerges betwe…

PredictionTrajectory Prediction

Assessment of a new GeoAI foundation model for flood inundation mapping

2023-09-25 · Wenwen Li, Hyunho Lee, Sizhe Wang, Chia-Yu Hsu 외

Vision foundation models are a new frontier in Geospatial Artificial Intelligence (GeoAI), an interdisciplinary research area that applies and extends AI for geospatial problem solving and geographic knowledge discovery,…

Flood Inundation MappingRepresentation Learning

LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series

2026-05-19 · Alexis Roger, Prateek Humane, Zhenghan Tai, Gwen Legate 외 arxiv

Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because language pretraining preconditions time series training with a reusa…