AI Paper Atlas

Research map / Benchmarks / CUB-200-2011

CUB-200-2011 leaderboard

177 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CUB-200-2011. Best accuracy: 94.3 (PMRC (SwinTransformer), CVPR 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.

CUB-200-2011 · accuracy

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

#accuracy ↑MethodPaperTopic
194.3PMRC (SwinTransformer)
SwinTransformer
Weakly Supervised Posture Mining for Fine-Grained Classification
CVPR 2023 · Table 3
Recognition and long-tail
292.9DHMamba (Ours)
VMamba
Disentangled Hypergraph-Guided Mamba Scanning for Fine-Grained Visual Recognition
AAAI 2026 · Table 1
Recognition and long-tail
392.8L-Bird+CUB-GT (MC)
Inception-v3
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
ECCV 2016 · Table 1
Recognition and long-tail
492.5MDCM
MS-ViT-Base
Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition
AAAI 2025 · Table 1
Attention and transformers
592.07Proposed feature recombination
ViT-B-16
Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and Method
TPAMI 2026 · Table (FGVC methods on CDLT an
Human and embodied modeling
692ViTree
SwinT-B
ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization
AAAI 2024 · Table 1
Human and embodied modeling
791.8MP-FGVC
ViT-B-16
Delving into Multimodal Prompting for Fine-Grained Visual Classification
AAAI 2024 · Table 1
CLIP and zero-shot
891.7TransFG
ViT-B_16
TransFG: A Transformer Architecture for Fine-Grained Recognition
AAAI 2022 · Table: Comparison of different
Attention and transformers
991.6ViT-NeT (SwinT-B)
SwinT-B
ViT-NeT: Interpretable Vision Transformers with Neural Tree Decoder
ICML 2022 · Table 1
Attention and transformers
1091.5Ours (DenseNet161)
DenseNet161
Learning Gabor Texture Features for Fine-Grained Recognition
ICCV 2023 · text
Recognition and long-tail
78 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

CUB-200-2011 · R@1

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

64 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

CUB-200-2011 · NMI

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

15 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

CUB-200-2011 · Top-1 Loc

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

#Top-1 Loc ↑MethodPaperTopic
187GenPromp
Stable Diffusion + EfficientNet-B7
Generative Prompt Model for Weakly Supervised Object Localization
ICCV 2023 · Table 1
Weakly supervised detection and segmentation
284.03Pro2SAM
Deit-S + SAM
Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization
ECCV 2024 · Table 1
Weakly supervised detection and segmentation
383.28C^2AM
DenseNet161; EfficientNet-B7
C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
CVPR 2022 · Table 1
Weakly supervised detection and segmentation
481.8CGTR
DeiT-S
Cross-token Guidance Transformer for Weakly Supervised Object Localization
ECCV 2026 · Table 1
Weakly supervised detection and segmentation
579.62CATR (Ours)
Deit-S
Category-aware Allocation Transformer for Weakly Supervised Object Localization
ICCV 2023 · Table 1
Weakly supervised detection and segmentation
677.4LCAR
ViT-S/16
Coarse2Fine: Local Consistency Aware Re-prediction for Weakly Supervised Object Localization
AAAI 2023 · Table 4
Weakly supervised detection and segmentation
776.75BAS
ResNet50
Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
IJCV 2023 · Table 1
Weakly supervised detection and segmentation
872ICE
DeiT-S
Adversarial Normalization: I Can Visualize Everything (ICE)
CVPR 2023 · Table 4
Attention and transformers
964.9CutMix + AdvCAM
ResNet-50
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
TPAMI 2022 · Table 7
Weakly supervised detection and segmentation
1062.29ADL
ResNet50-SE
Attention-Based Dropout Layer for Weakly Supervised Object Localization
CVPR 2019 · Table 3
Weakly supervised detection and segmentation
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.