AI Paper Atlas

Research map / Benchmarks / FGVC-Aircraft

FGVC-Aircraft leaderboard

62 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on FGVC-Aircraft. Best accuracy: 96.7 (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.

FGVC-Aircraft · accuracy

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

#accuracy ↑MethodPaperTopic
196.7PMRC (SwinTransformer)
SwinTransformer
Weakly Supervised Posture Mining for Fine-Grained Classification
CVPR 2023 · Table 3
Recognition and long-tail
295.9L-Aircraft+FGVC-GT (MC)
Inception-v3
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
ECCV 2016 · Table 1
Recognition and long-tail
394.8Ours
ResNet50
Trusted Fine-Grained Image Classification through Hierarchical Evidence Fusion
AAAI 2023 · Table 2
Recognition and long-tail
494.3GaRD (ResNet50)
ResNet-50
Graph-Based High-Order Relation Discovery for Fine-Grained Recognition
CVPR 2021 · Table 2
Open-set and few-shot detection
594.2Baseline + CAL
ResNet-101
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-Identification
ICCV 2021 · Table 1
Recognition and long-tail
693.9DP-Net
ResNet-50
Dynamic Position-aware Network for Fine-grained Image Recognition
AAAI 2021 · Table 3
Human and embodied modeling
793.8DF-GMM
ResNet-50
Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative Learning
CVPR 2020 · Table 5
Recognition and long-tail
893.6Ours_PMG
PMG
Your "Flamingo" is My "Bird": Fine-Grained, or Not
CVPR 2021 · Table: Performance comparisons
Recognition and long-tail
993.5Ours (multi scale)
ResNet-50
Fine-Grained Recognition: Accounting for Subtle Differences between Similar Classes
AAAI 2020 · Table: Experimental results on
Recognition and long-tail
1093.4PMG (Combined Accuracy)
ResNet50
Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
ECCV 2020 · Table 1
Recognition and long-tail
52 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.