arXiv:2611.25902v1 cs.CV

Does It Depend on the Split? Frozen Satellite Features vs. Fine-Tuned CNNs for Tree Species Mapping

Dharani Deivasihamani, Nandakishore Puttashamachar

제출 2026-11-20

원문 초록

Self-supervised foundation models are often said to need fewer labels than supervised training. We test this on a forestry task: classifying 20 tree species classes in 0.2 m aerial images from the TreeSatAI dataset. We compare a frozen DINOv3 model pretrained on 493 million satellite images, with only a linear classifier trained on top, against an ImageNet ResNet-50 that is fine-tuned end to end. On the official split, fine-tuning wins clearly (macro F1 0.764 vs. 0.685). However, 28.8% of the official test patches overlap a training or validation patch, and copying the label of the nearest such patch is correct for 83.6% of them. We therefore build a spatial split that holds out whole 2 km squares with a 200 m buffer. On this split the comparison becomes inconclusive (0.648 vs. 0.640, paired 95% CI of the difference [-0.054, 0.016]), and the learning curves of the two models overlap at every label budget from 343 to 33,126 training patches. On the five rarest classes, the frozen model achieves a higher mean F1 (0.566 vs. 0.445), although the confidence interval for this difference includes zero ([-0.05, 0.23]). Diagnostics show that the frozen features mainly miss differences between closely related species, such as the two native oaks. Choosing the input size and layer on validation data (224 px, block 16) raises the frozen model to 0.662 on the spatial split. A comparison that looks decisive on the official split is thus inconclusive under geographically separated evaluation. We release the spatial split and our code.

제출 이력

확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.

  1. arXiv:2611.25902v1제출 시각 미확인

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

공통 태그로 연결된 공개 논문이 아직 없습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.