| Unicom: Universal and Compact Representation Learning for Image Retrieval | ✓ Link | 90.1 | Unicom+ViT-L@336px | 2023-04-12 |
| Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning | ✓ Link | 88.5 | EfficientDML-VPTSP-G/512 | 2024-02-04 |
| Hyperbolic Vision Transformers: Combining Improvements in Metric Learning | ✓ Link | 85.6 | Hyp-ViT | 2022-03-21 |
| Calibrated neighborhood aware confidence measure for deep metric learning | | 74.9 | NED | 2020-06-08 |
| Center Contrastive Loss for Metric Learning | | 73.45 | CCL (ResNet-50) | 2023-08-01 |
| Attributable Visual Similarity Learning | ✓ Link | 71.9 | ResNet-50 + AVSL | 2022-03-28 |
| Learning Intra-Batch Connections for Deep Metric Learning | ✓ Link | 71.8 | ResNet-50 + Intra-Batch Connections | 2021-02-15 |
| It Takes Two to Tango: Mixup for Deep Metric Learning | ✓ Link | 71.4 | ResNet-50 + Metrix | 2021-06-09 |
| Integrating Language Guidance into Vision-based Deep Metric Learning | ✓ Link | 71.4 | ResNet50 + Language | 2022-03-16 |
| Proxy Anchor Loss for Deep Metric Learning | ✓ Link | 71.1 | BN-Inception + Proxy-Anchor | 2020-03-31 |
| Non-isotropy Regularization for Proxy-based Deep Metric Learning | ✓ Link | 70.5 | ResNet50 + NIR | 2022-03-16 |
| S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning | ✓ Link | 70.1 | ResNet50 + S2SD | 2020-09-17 |
| A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses | ✓ Link | 69.2 | ResNet-50 + Cross-Entropy | 2020-03-19 |
| DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning | ✓ Link | 69.2 | ResNet50 + DiVA | 2020-04-28 |
| ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis | ✓ Link | 69.0 | ResNet-50 + ProxyNCA++ | 2020-04-02 |
| Towards Interpretable Deep Metric Learning with Structural Matching | ✓ Link | 68.15 | MS + DIML | 2021-08-12 |
| PADS: Policy-Adapted Sampling for Visual Similarity Learning | ✓ Link | 67.3 | ResNet50 (128) + PADS | 2020-03-24 |
| Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings | ✓ Link | 66.8 | ABE + HORDE | 2019-08-07 |
| MIC: Mining Interclass Characteristics for Improved Metric Learning | ✓ Link | 66.1 | ResNet50 (128) + MIC | 2019-09-25 |
| The Group Loss for Deep Metric Learning | ✓ Link | 65.5 | BN-Inception + Group Loss | 2019-12-01 |
| SoftTriple Loss: Deep Metric Learning Without Triplet Sampling | ✓ Link | 65.4 | BN-Inception + SoftTriple | 2019-09-11 |
| Improved Embeddings with Easy Positive Triplet Mining | ✓ Link | 64.9 | EPSHN(512) | 2019-04-08 |
| Dissecting the impact of different loss functions with gradient surgery | | 63.8 | Gradient Surgery | 2022-01-27 |
| Sampling Matters in Deep Embedding Learning | ✓ Link | 63.6 | ResNet-50 + Margin | 2017-06-23 |
| Hard-Aware Deeply Cascaded Embedding | ✓ Link | 60.7 | HDC | 2016-11-17 |
| Attention-based Ensemble for Deep Metric Learning | | 60.6 | ABE-8-512 | 2018-04-02 |
| Local Similarity-Aware Deep Feature Embedding | | 58.3 | PDDM Quadruplet | 2016-10-27 |
| Hard negative examples are hard, but useful | ✓ Link | 57.7 | SCT(64) | 2020-07-24 |
| Improved Embeddings with Easy Positive Triplet Mining | ✓ Link | 57.3 | EPSHN(64) | 2019-04-08 |
| Hardness-Aware Deep Metric Learning | ✓ Link | 53.7 | GoogLeNet + HDML | 2019-03-13 |