RESISC45

Dataset Information
Modalities
Images
Introduced
2017
License
Unspecified
Homepage
Official Website
Contents

Overview

RESISC45 dataset is a dataset for Remote Sensing Image Scene Classification (RESISC). It contains 31,500 RGB images of size 256×256 divided into 45 scene classes, each class containing 700 images. Among its notable features, RESISC45 contains varying spatial resolution ranging from 20cm to more than 30m/px.

Variants: RESISC45

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Image Classification LWGANet L0 LWGANet: A Lightweight Group Attention … 2025-01-17
Image Classification LWGANet L2 LWGANet: A Lightweight Group Attention … 2025-01-17
Image Classification LWGANet L1 LWGANet: A Lightweight Group Attention … 2025-01-17
Image Classification SAG-ViT SAG-ViT: A Scale-Aware, High-Fidelity Patching … 2024-11-14
Image Clustering TURTLE (CLIP + DINOv2) Let Go of Your Labels … 2024-06-11
Image Classification SkySense-O SkySense: A Multi-Modal Remote Sensing … 2023-12-15
Image Classification AGOS All Grains, One Scheme (AGOS): … 2022-05-06
Image Classification SwAV (ResNet50-w5) Vision Models Are More Robust … 2022-02-16
Image Classification DINO (DeiT-B/16) Vision Models Are More Robust … 2022-02-16
Image Classification MoCo-v3 (ViT-B/16) Vision Models Are More Robust … 2022-02-16
Image Classification CLIP (ViT-B/16) Vision Models Are More Robust … 2022-02-16
Image Classification DeiT-B/16 Vision Models Are More Robust … 2022-02-16
Image Classification SimCLR-v2 (ResNet152-w3 + SK) Vision Models Are More Robust … 2022-02-16
Image Classification ResNet50 (ImageNet-supervised) Vision Models Are More Robust … 2022-02-16
Image Classification MoCo-v2 (ResNet50) Vision Models Are More Robust … 2022-02-16
Image Classification SEER (RegNet10B) Vision Models Are More Robust … 2022-02-16
Image Classification ResNet50 In-domain representation learning for remote … 2019-11-15

Research Papers

Recent papers with results on this dataset:

External Links: