pith. sign in

arxiv: 2406.07032 · v1 · pith:3F3TCOZ3new · submitted 2024-06-11 · 💻 cs.CV

RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks

classification 💻 cs.CV
keywords remotesensinginformationmodelacrossdownstreamfoundationmapping
0
0 comments X
read the original abstract

Remote sensing lightweight foundation models have achieved notable success in online perception within remote sensing. However, their capabilities are restricted to performing online inference solely based on their own observations and models, thus lacking a comprehensive understanding of large-scale remote sensing scenarios. To overcome this limitation, we propose a Remote Sensing Distributed Foundation Model (RS-DFM) based on generalized information mapping and interaction. This model can realize online collaborative perception across multiple platforms and various downstream tasks by mapping observations into a unified space and implementing a task-agnostic information interaction strategy. Specifically, we leverage the ground-based geometric prior of remote sensing oblique observations to transform the feature mapping from absolute depth estimation to relative depth estimation, thereby enhancing the model's ability to extract generalized features across diverse heights and perspectives. Additionally, we present a dual-branch information compression module to decouple high-frequency and low-frequency feature information, achieving feature-level compression while preserving essential task-agnostic details. In support of our research, we create a multi-task simulation dataset named AirCo-MultiTasks for multi-UAV collaborative observation. We also conduct extensive experiments, including 3D object detection, instance segmentation, and trajectory prediction. The numerous results demonstrate that our RS-DFM achieves state-of-the-art performance across various downstream tasks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis

    cs.LG 2025-06 unverdicted novelty 6.0

    TESSERA learns robust label-efficient embeddings from irregular multi-modal EO time series via Barlow Twins plus global shuffling and mix-based regularizers, delivering SOTA accuracy on classification, segmentation an...