How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?
원문 초록
Self-supervised pre-training has proven highly effective for many computer vision tasks, particularly when labelled data are scarce. In the context of Earth Observation (EO), foundation models and various other Vision Transformer (ViT)-based approaches have been successfully applied for transfer learning to downstream tasks. However, it remains unclear under which conditions pre-trained models offer significant advantages over training from scratch. In this study, we investigate the effectiveness of pre-training ViT-based Masked Autoencoders (MAE) for downstream EO tasks, focusing on reconstruction, segmentation, and classification. We consider two large ViT-based MAE pre-trained models: a foundation model (Prithvi) and SatMAE. We evaluate Prithvi on reconstruction and segmentation-based downstream tasks, and for SatMAE we assess its performance on a classification downstream task. Our findings suggest that pre-training is particularly beneficial when the fine-tuning task closely resembles the pre-training task, e.g. reconstruction. In contrast, for tasks such as segmentation or classification, training from scratch with specific hyperparameter adjustments proved to be equally or more effective.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation
Semantic Segmentation Using Transfer Learning on Fisheye Images
FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery
Cross-Domain Few-Shot Semantic Segmentation
Class Attention Network for Semantic Segmentation of Remote Sensing Images
토론
이 논문과 연결된 포럼 글이 아직 없습니다.