AI Paper Atlas

Research map / Benchmarks / NABirds

NABirds leaderboard

20 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NABirds. Best accuracy: 92 (DHMamba (Ours), AAAI 2026).

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.

NABirds · accuracy

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

#accuracy ↑MethodPaperTopic
192DHMamba (Ours)
VMamba
Disentangled Hypergraph-Guided Mamba Scanning for Fine-Grained Visual Recognition
AAAI 2026 · Table 1
Recognition and long-tail
292MDCM
MS-ViT-Base
Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition
AAAI 2025 · Table 2
Attention and transformers
391MP-FGVC
ViT-B-16
Delving into Multimodal Prompting for Fine-Grained Visual Classification
AAAI 2024 · Table 2
CLIP and zero-shot
491CAPContext-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
AAAI 2021 · Table 1
CNN features
590.8TransFG
ViT-B_16
TransFG: A Transformer Architecture for Fine-Grained Recognition
AAAI 2022 · Table: Comparison of different
Attention and transformers
690.1LOFF-TA + Pool
DINOv2 ViT-G
Learning from Offline Foundation Features with Tensor Augmentations
NeurIPS 2024 · Main results table
RNNs and normalization
788.6MGE-CNN
ResNet-101
Learning a Mixture of Granularity-Specific Experts for Fine-Grained Categorization
ICCV 2019 · Table 2
Recognition and long-tail
888.1API-Net
DenseNet-161
Learning Attentive Pairwise Interaction for Fine-Grained Classification
AAAI 2020 · Table: Comparison with The-Sta
Recognition and long-tail
988GaRD (ResNet50)
ResNet-50
Graph-Based High-Order Relation Discovery for Fine-Grained Recognition
CVPR 2021 · Table 4
Open-set and few-shot detection
1087.89Subset B (585-class)
Inception-v3
Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
CVPR 2018 · Table: transfer learning perfo
Domain adaptation and generalization
10 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.