AI Paper Atlas

Research map / Benchmarks / iNaturalist

iNaturalist leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on iNaturalist. Best accuracy: 75.3 (NAO-centroid, NeurIPS 2023).

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.

iNaturalist · accuracy

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

#accuracy ↑MethodPaperTopic
175.3NAO-centroid
ResNet-50
Norm-guided latent space exploration for text-to-image generation
NeurIPS 2023 · Few-shot and long-tail results
Text-to-image diffusion
272.7Semantic softmax + KD
TResNet-M
ImageNet-21K Pretraining for the Masses
NeurIPS 2021 · Table, Comparing downstream re
Attention and transformers
370.2IEM + RSA
ResNet-50
Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition
CVPR 2020 · Table 2
Recognition and long-tail
469.7DRO-LT learned eps
ResNet-50
Distributional Robustness Loss for Long-Tail Learning
ICCV 2021 · Table 3
Recognition and long-tail
569.01ECRT-MPSupercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer
NeurIPS 2021 · Table 1
Recognition and long-tail
666.22SatCLIP L=40SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery
AAAI 2025 · Table: Downstream task perform
Recognition and long-tail
763.45Concept-RuleNet
LLaVA-1.6
Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models
AAAI 2026 · Table 1
Multimodal LLMs
860.7iSICE
ResNet-50
Learning Partial Correlation Based Deep Visual Representation for Image Classification
CVPR 2023 · Table: Comparison between iSIC
CNN design
959.4HiMulConE
ResNet-50
Use All the Labels: A Hierarchical Multi-Label Contrastive Learning Framework
CVPR 2022 · Table 1
Self-supervised and contrastive
1047.8FedGWCInteraction-Aware Gaussian Weighting for Clustered Federated Learning
ICML 2025 · Table 2
Personalized and heterogeneous FL
1 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.