AI Paper Atlas

Research map / Benchmarks / AID

AID leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on AID. Best accuracy: 97.4 (LookWhere (k=185), NeurIPS 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

AID · accuracy

12 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
197.4LookWhere (k=185)
DINOv2 ViT-Base
LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
NeurIPS 2025 · AID results table
Attention and transformers
294.6LOFF-TA + Pool
DINOv2 ViT-G
Learning from Offline Foundation Features with Tensor Augmentations
NeurIPS 2024 · Main results table
RNNs and normalization
392.43RingMo-Agent (FT)RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning
TPAMI 2026 · Table (AID and NWPU-RESISC45)
Multimodal LLMs
491.7VHM
Vicuna-v1.5 7B
VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis
AAAI 2025 · Scene classification results t
Visual question answering
591.26LHRS-Bot
LLaMA2-7B
LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model
ECCV 2024 · Table 1
Multimodal LLMs
688.84QuCNetQuCNet: Quantum Deep Learning Driven Multi-Circuit Network for Remote Sensing Image Classification
CVPR 2026 · Table 1
CNN design
788.76EarthDial
InternViT-300M + Phi-3-mini
EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
CVPR 2025 · Table: classification accuracy
Multimodal LLMs
885.83SIOFSStray Intrusive Outliers-Based Feature Selection on Intra-Class Asymmetric Instance Distribution or Multiple High-Density Clusters
ICML 2025 · Table 3
Recognition and long-tail
982.93SkySense-O†SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling
CVPR 2025 · Table 4
CLIP and zero-shot
1080.9TEOChat
Video-LLaVA
TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data
ICLR 2025 · Single image accuracies table
Visual question answering
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.