Metric Learning On Cars196
평가 지표
R@1
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | R@1 |
|---|---|
| dissecting-the-impact-of-different-loss | 86.5 |
| hyperbolic-vision-transformers-combining | 89.2 |
| hyperbolic-vision-transformers-combining | 86.5 |
| proxy-anchor-loss-for-deep-metric-learning | 88.3 |
| das-densely-anchored-sampling-for-deep-metric | 88.34 |
| the-group-loss-for-deep-metric-learning | 85.6 |
| attention-based-ensemble-for-deep-metric | 85.2 |
| pads-policy-adapted-sampling-for-visual | 83.5 |
| das-densely-anchored-sampling-for-deep-metric | 87.8 |
| hard-negative-examples-are-hard-but-useful | 73.2 |
| towards-interpretable-deep-metric-learning | 87.01 |
| learning-intra-batch-connections-for-deep | 88.1 |
| learning-semantic-proxies-from-visual-prompts | 91.2 |
| improved-embeddings-with-easy-positive | 82.7 |
| calibrated-neighborhood-aware-confidence | 91.5 |
| sampling-matters-in-deep-embedding-learning | 79.6 |
| recall-k-surrogate-loss-with-large-batches | 88.3 |
| metric-learning-with-horde-high-order | 88.0 |
| it-takes-two-to-tango-mixup-for-deep-metric | 89.6 |
| recall-k-surrogate-loss-with-large-batches | 89.5 |
| hardness-aware-deep-metric-learning | 79.1 |
| s2sd-simultaneous-similarity-based-self | 89.5 |
| unicom-universal-and-compact-representation | 98.2 |
| metric-learning-cross-entropy-vs-pairwise | 89.3 |
| diva-diverse-visual-feature-aggregation | 87.6 |
| non-isotropy-regularization-for-proxy-based | 89.1 |
| hyperbolic-vision-transformers-combining | 92.8 |
| integrating-language-guidance-into-vision | 90.2 |
| proxynca-revisiting-and-revitalizing-proxy | 86.5 |
| attributable-visual-similarity-learning | 91.5 |
| softtriple-loss-deep-metric-learning-without | 84.5 |
| center-contrastive-loss-for-metric-learning | 91.02 |
| circle-loss-a-unified-perspective-of-pair | 83.4 |
| improved-embeddings-with-easy-positive | 75.5 |
| learning-intra-batch-connections-for-deep | 91.5 |
| mic-mining-interclass-characteristics-for | 82.6 |