AI Paper Atlas

Research map / Benchmarks / Stanford Cars

Stanford Cars leaderboard

123 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Stanford Cars. Best accuracy: 96.9 (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.

Stanford Cars · accuracy

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

#accuracy ↑MethodPaperTopic
196.9PMRC (SwinTransformer)
SwinTransformer
Weakly Supervised Posture Mining for Fine-Grained Classification
CVPR 2023 · Table 3
Recognition and long-tail
296.7DHMamba (Ours)
VMamba
Disentangled Hypergraph-Guided Mamba Scanning for Fine-Grained Visual Recognition
AAAI 2026 · Table 1
Recognition and long-tail
396.37SCalDA
ResNet-50 (ImageNet-1K pretrained)
SCalDA: Semantics-Calibrated and Diffusion-Enhanced Data Augmentation
ICML 2026 · Table 1
Autoregressive and latent generation
496.1w/ feat. traj. & SEQ
CLIP-ViT-L/14 frozen
Learning Time in Static Classifiers
AAAI 2026 · Table 1
Action recognition
595.7CAPContext-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
AAAI 2021 · Table 1
CNN features
695.5Baseline + CAL
ResNet-101
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-Identification
ICCV 2021 · Table 1
Recognition and long-tail
795.3Baseline + DCAL
R50-ViT-Base
Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification
CVPR 2022 · FGVC results table
CNN features
895.3API-Net
DenseNet-161
Learning Attentive Pairwise Interaction for Fine-Grained Classification
AAAI 2020 · Table: Comparison with The-Sta
Recognition and long-tail
995.12Diff-Mix
ResNet50
Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
CVPR 2024 · Table 1
Text-to-image diffusion
1095.1ViTree
SwinT-B
ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization
AAAI 2024 · Table 1
Human and embodied modeling
102 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

Stanford Cars · FID

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

#FID ↓MethodPaperTopic
14.38Domain Guidance
DiT-XL/2-256x256
Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model
ICLR 2025 · Table: Comparisons on downstre
Fast diffusion sampling
24.43WAT
DiT-XL/2-256
Wasserstein-Aware Transfer: Class-Level Alignment for Robust Diffusion Model Adaptation
AAAI 2026 · Table 1
Text-to-image diffusion
35.37Diff-Tuning
DiT-XL-2-256x256
Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
NeurIPS 2024 · Table 1
Fast diffusion sampling
46.48MixNMatch
FineGAN
MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
CVPR 2020 · Image quality & diversity tabl
Autoregressive and latent generation
56.77VisCoIN
ResNet50 + StyleGAN2-ADA
Restyling Unsupervised Concept Based Interpretable Networks with Generative Models
ICLR 2025 · Table 2a
Recognition and long-tail
613.4Ours
Stable Diffusion LDM
Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models
ICCV 2023 · Table 3
Fast diffusion sampling
716.03FineGANFineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
CVPR 2019 · Table 1
Open-set and few-shot detection
824.27CoordGANCoordGAN: Self-Supervised Dense Correspondences Emerge From GANs
CVPR 2022 · Table 2
GANs
928.36AND-OR modelInducing Hierarchical Compositional Model by Sparsifying Generator Network
CVPR 2020 · Table: Comparisons of the Fréc
Autoregressive and latent generation
1034.17DS-ComGANComGAN: Unsupervised Disentanglement and Segmentation via Image Composition
NeurIPS 2022 · Table 1
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.