AI Paper Atlas

Research map / Benchmarks / iNaturalist 2018

iNaturalist 2018 leaderboard

41 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on iNaturalist 2018. Best accuracy: 84.1 (Omnivore (Swin-L, higher resolution), CVPR 2022).

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 2018 · accuracy

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

#accuracy ↑MethodPaperTopic
184.1Omnivore (Swin-L, higher resolution)
Swin-L
Omnivore: A Single Model for Many Visual Modalities
CVPR 2022 · Table: image classification fi
Cross-modal learning
283.673Dynamic MLP
SK-Res2Net-101
Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information
CVPR 2022 · Table 1
Human and embodied modeling
383.2OmniMAE ViT-H
ViT-H
OmniMAE: Single Model Masked Pretraining on Images and Videos
CVPR 2023 · Table: Comparing OmniMAE with
Video segmentation and tracking
481.3Low-rank Mixer (LoSA)
ViT-g
Time- Memory- and Parameter-Efficient Visual Adaptation
CVPR 2024 · Table 3
Pruning and efficient tuning
581LiVT (384 resolution)
ViT-Base-16
Learning Imbalanced Data With Vision Transformers
CVPR 2023 · Table: Top-1 accuracy of ResNe
Attention and transformers
681VL-LTR-384
ViT-Base/16 (CLIP init), 384 input
VL-LTR: Learning Class-Wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
ECCV 2022 · Table 3
Recognition and long-tail
780.9Sage
CLIP ViT-B/16
Semantic-Guided Fine-Tuning of Foundation Model for Long-Tailed Visual Recognition
IJCV 2026 · Table 4
Recognition and long-tail
878.2MixMAE
Swin-B/W14
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
CVPR 2023 · Classification transfer table
Attention and transformers
976.9TCL
ResNet-50
Trust-calibrated Collaborative Learning for Long-Tailed Visual Recognition
CVPR 2026 · Table 3
Recognition and long-tail
1076.8HGLTR
ViT-B/16
HGLTR: Hierarchical Knowledge Injection for Calibrating Pre-trained Models in Long-Tail Recognition
AAAI 2026 · Table 4
Recognition and long-tail
31 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.