PyViT-FUSE: A Foundation Model for Multi-Sensor Earth Observation Data

• URL: http://arxiv.org/abs/2504.18770v1
• Date: Sat, 26 Apr 2025 02:34:33 GMT
• Title: PyViT-FUSE: A Foundation Model for Multi-Sensor Earth Observation Data
• Authors: Manuel Weber, Carly Beneke,
• Abstract summary: We propose PyViT-FUSE, a foundation model for earth observation data explicitly designed to handle multi-modal imagery.<n>We train the model on a globally sampled dataset in a self-supervised manner, leveraging core concepts of the SwAV algorithm.<n>We show the interpretability of the fusion mechanism by visualization of the attention scores and the models applicability to downstream tasks.
• Score: 0.2209921757303168
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose PyViT-FUSE, a foundation model for earth observation data explicitly designed to handle multi-modal imagery by learning to fuse an arbitrary number of mixed-resolution input bands into a single representation through an attention mechanism. The learned patch tokens are further processed by a stack of vision transformers with a novel pyramidal structure. We train the model on a globally sampled dataset in a self-supervised manner, leveraging core concepts of the SwAV algorithm. We show the interpretability of the fusion mechanism by visualization of the attention scores and the models applicability to downstream tasks.

Related papers

• Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation [61.64052577026623]
  Real-world multi-view datasets are often heterogeneous and imperfect.<n>We propose a novel robust MVL method (namely RML) with simultaneous representation fusion and alignment.<n>In experiments, we employ it in unsupervised multi-view clustering, noise-label classification, and as a plug-and-play module for cross-modal hashing retrieval.
  arXiv  Detail & Related papers  (2025-03-06T07:01:08Z)
• Multi-view Aggregation Network for Dichotomous Image Segmentation [76.75904424539543]
  Dichotomous Image (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. Existing methods rely on tedious multiple encoder-decoder streams and stages to gradually complete the global localization and local refinement. Inspired by it, we model DIS as a multi-view object perception problem and provide a parsimonious multi-view aggregation network (MVANet) Experiments on the popular DIS-5K dataset show that our MVANet significantly outperforms state-of-the-art methods in both accuracy and speed.
  arXiv  Detail & Related papers  (2024-04-11T03:00:00Z)
• Neural Clustering based Visual Representation Learning [61.72646814537163]
  Clustering is one of the most classic approaches in machine learning and data analysis. We propose feature extraction with clustering (FEC), which views feature extraction as a process of selecting representatives from data. FEC alternates between grouping pixels into individual clusters to abstract representatives and updating the deep features of pixels with current representatives.
  arXiv  Detail & Related papers  (2024-03-26T06:04:50Z)
• One for All: Toward Unified Foundation Models for Earth Vision [24.358013737755822]
  Current remote sensing foundation models specialize in a single modality or a specific spatial resolution range. We introduce OFA-Net: employing a single, shared Transformer backbone for multiple data modalities with different spatial resolutions. The proposed method is evaluated on 12 distinct downstream tasks and demonstrates promising performance.
  arXiv  Detail & Related papers  (2024-01-15T08:12:51Z)
• Multi-View Unsupervised Image Generation with Cross Attention Guidance [23.07929124170851]
  This paper introduces a novel pipeline for unsupervised training of a pose-conditioned diffusion model on single-category datasets. We identify object poses by clustering the dataset through comparing visibility and locations of specific object parts. Our model, MIRAGE, surpasses prior work in novel view synthesis on real images.
  arXiv  Detail & Related papers  (2023-12-07T14:55:13Z)
• Vision Transformers Need Registers [26.63912173005165]
  We identify and characterize artifacts in feature maps of both supervised and self-supervised ViT networks. We show that this solution fixes that problem entirely for both supervised and self-supervised models.
  arXiv  Detail & Related papers  (2023-09-28T16:45:46Z)
• With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning [47.96387857237473]
  We devise a network which can perform attention over activations obtained while processing other training samples. Our memory models the distribution of past keys and values through the definition of prototype vectors. We demonstrate that our proposal can increase the performance of an encoder-decoder Transformer by 3.7 CIDEr points both when training in cross-entropy only and when fine-tuning with self-critical sequence training.
  arXiv  Detail & Related papers  (2023-08-23T18:53:00Z)
• Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection [33.210575826086654]
  We present a weakly-supervised RGB-D salient object detection model via supervision. We focus on effective multimodal representation learning via inter-modal mutual information regularization.
  arXiv  Detail & Related papers  (2023-06-06T12:36:57Z)
• AttentionViz: A Global View of Transformer Attention [60.82904477362676]
  We present a new visualization technique designed to help researchers understand the self-attention mechanism in transformers. The main idea behind our method is to visualize a joint embedding of the query and key vectors used by transformer models to compute attention. We create an interactive visualization tool, AttentionViz, based on these joint query-key embeddings.
  arXiv  Detail & Related papers  (2023-05-04T23:46:49Z)
• STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition [50.064502884594376]
  We study the problem of human action recognition using motion capture (MoCap) sequences. We propose a novel Spatial-Temporal Mesh Transformer (STMT) to directly model the mesh sequences. The proposed method achieves state-of-the-art performance compared to skeleton-based and point-cloud-based models.
  arXiv  Detail & Related papers  (2023-03-31T16:19:27Z)
• EnfoMax: Domain Entropy and Mutual Information Maximization for Domain Generalized Face Anti-spoofing [0.0]
  Face anti-spoofing (FAS) method performs well under intra-domain setups. The domain generalization (DG) method has gained more attention in FAS. This paper proposes the EnfoMax framework, which uses information theory to analyze cross-domain FAS tasks.
  arXiv  Detail & Related papers  (2023-02-17T03:54:18Z)
• Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency [114.02182755620784]
  We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our framework is shown to outperform the state-of-the-art depth and motion estimation methods.
  arXiv  Detail & Related papers  (2021-02-04T14:26:42Z)

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.