Papers with Code · CC BY-SA 4.0

RESISC45

아카이브 평가 20건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
ResNet50	Top 1 Accuracy 96.83	In-domain representation learning for remote sensing 2019-11-15	코드 1
LWGANet L2	Top 1 Accuracy 96.17	LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks 2025-01-17	코드 1
DecoupleNet D2	Top 1 Accuracy 95.87	DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks 2024-09-23	코드 1
LWGANet L1	Top 1 Accuracy 95.70	LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks 2025-01-17	코드 1
SEER (RegNet10B)	Top 1 Accuracy 95.61	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
LWGANet L0	Top 1 Accuracy 95.49	LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks 2025-01-17	코드 1
AGOS	Top 1 Accuracy 94.91	All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification 2022-05-06	코드 1
SwAV (ResNet50-w5)	Top 1 Accuracy 94.73	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
DINO (DeiT-B/16)	Top 1 Accuracy 93.97	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
LSENet	Top 1 Accuracy 93.49	Local semantic enhanced convnet for aerial scene recognition 2021-07-08	코드 1
MoCo-v3 (ViT-B/16)	Top 1 Accuracy 93.35	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
CLIP (ViT-B/16)	Top 1 Accuracy 92.7	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
BYOL (ResNet200-w2)	Top 1 Accuracy 92.53	연결 없음 논문 날짜 미기재	연결 없음
DeiT-B/16	Top 1 Accuracy 92.48	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
SimCLR-v2 (ResNet152-w3 + SK)	Top 1 Accuracy 89.77	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
ResNet50 (ImageNet-supervised)	Top 1 Accuracy 88.56	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
MIDC-Net	Top 1 Accuracy 87.99	A multiple-instance densely-connected ConvNet for aerial scene classification 2020-03-03	코드 1
MoCo-v2 (ResNet50)	Top 1 Accuracy 85.4	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 2022-02-16	코드 1
SAG-ViT	F1 95.49	SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers 2024-11-14	코드 1
SkySense-O	zero-shot Acc 83.28	SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery 2023-12-15	코드 1