AI Paper Atlas

Research map / Benchmarks / Cars196

Cars196 leaderboard

77 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Cars196. Best R@1: 94.7 (Potential Field, CVPR 2025).

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.

Cars196 · R@1

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

#R@1 ↑MethodPaperTopic
194.7Potential Field
DINO
Potential Field Based Deep Metric Learning
CVPR 2025 · Table 1
Recognition and long-tail
294.7SGSL
ResNet-50
Stop-Gradient Softmax Loss for Deep Metric Learning
AAAI 2023 · Table 1
Implicit bias and generalization
393.1GCA-HNG
DINO-S DN384, PA loss
Globally Correlation-Aware Hard Negative Generation
IJCV 2024 · Table 1
Graph self-supervised learning
492.1PA+DADA(R50)
ResNet50
Towards Improved Proxy-Based Deep Metric Learning via Data-Augmented Domain Adaptation
AAAI 2024 · Table 1
Domain adaptation and generalization
591.8MetricFormer-PA
ResNet-50
MetricFormer: A Unified Perspective of Correlation Exploring in Similarity Learning
NeurIPS 2022 · Table 2
Recognition and long-tail
691.5ProxyAnchor-AVSL
ProxyAnchor
Attributable Visual Similarity Learning
CVPR 2022 · Table 1
Recognition and long-tail
791.5Proposed512
ResNet-50
Learning Better Visual Data Similarities via New Grouplet Non-Euclidean Embedding
ICCV 2021 · Table 1
Graph algorithms and clustering
891.2VPTSP-G (ViT-B16/512)
ViT-B16/512
Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
ICLR 2024 · Table: comparison with state-o
CLIP and zero-shot
991.2Cross-Image-Attention (Ours)
ResNet-50
Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning
CVPR 2023 · Table 1
Autoregressive and latent generation
1091.16CRT
MiT-B2
Coded Residual Transform for Generalizable Deep Metric Learning
NeurIPS 2022 · Comparison of retrieval perfor
Recognition and long-tail
67 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

Cars196 · NMI

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

8 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.