mlsanityData to 7 Oct 2026

Attention-based Ensemble for Deep Metric Learning

arXiv 1804.00382 ↗First posted 2 Apr 2018cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

Deep metric learning aims to learn an embedding function, modeled as deep neural network. This embedding function usually puts semantically similar images close while dissimilar images far from each other in the learned embedding space. Recently, ensemble has been applied to deep metric learning to yield state-of-the-art results. As one important aspect of ensemble, the learners should be diverse in their feature embeddings. To this end, we propose an attention-based ensemble, which uses multiple attention masks, so that each learner can attend to different parts of the object. We also propose a divergence loss, which encourages diversity among the learners. The proposed method is applied to the standard benchmarks of deep metric learning and experimental results show that it outperforms the state-of-the-art methods by a significant margin on image retrieval tasks.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 17; 2023: 8; 2024: 7; 2025: 0; 2026: 2.

56 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 109
  3. 2021Training Vision Transformers for Image Retrievalcited by 90
  4. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  5. 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
  6. 2021Learning Intra-Batch Connections for Deep Metric Learningcited by 34
  7. 2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
  8. 2021Deep Relational Metric Learningcited by 22
  9. 2021Embedding Transfer with Label Relaxation for Improved Metric Learningcited by 21
  10. 2021Learning with Memory-based Virtual Classes for Deep Metric Learningcited by 21
  11. 2022Integrating Language Guidance into Vision-based Deep Metric Learningcited by 19
  12. 2021Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learningcited by 17
38 more
  1. 2021Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learningcited by 17
  2. 2021Orthogonal Ensemble Networks for Biomedical Image Segmentationcited by 16
  3. 2022Self-Taught Metric Learning without Labelscited by 13
  4. 2022Attributable Visual Similarity Learningcited by 12
  5. 2024Understanding Hyperbolic Metric Learning through Hard Negative Samplingcited by 10
  6. 2021Adaptive Hierarchical Similarity Metric Learning with Noisy Labelscited by 8
  7. 2022Contrastive Bayesian Analysis for Deep Metric Learningcited by 8
  8. 2023Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatchcited by 8
  9. 2021LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learningcited by 7
  10. 2023Introspective Deep Metric Learningcited by 7
  11. 2021Multi-level Distance Regularization for Deep Metric Learningcited by 6
  12. 2022The Group Loss++: A deeper look into group loss for deep metric learningcited by 6
  13. 2024V2M: Visual 2-Dimensional Mamba for Image Representation Learningcited by 6
  14. 2021Group Contrastive Self-Supervised Learning on Graphscited by 5
  15. 2021Improving Deep Metric Learning by Divide and Conquercited by 5
  16. 2022DAS: Densely-Anchored Sampling for Deep Metric Learningcited by 5
  17. 2021Multi-Head Deep Metric Learning Using Global and Local Representationscited by 4
  18. 2021Rethinking Deep Contrastive Learning with Embedding Memorycited by 3
  19. 2021Atlas Based Representation and Metric Learning on Manifoldscited by 3
  20. 2022Adaptive neighborhood Metric learningcited by 3
  21. 2022BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Taskcited by 3
  22. 2022Deep Metric Learning with Chance Constraintscited by 3
  23. 2022Rethinking Batch Sample Relationships for Data Representation: A Batch-Graph Transformer based Approachcited by 2
  24. 2023Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applicationscited by 2
  25. 2024FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learningcited by 2
  26. 2021Hotel Recognition via Latent Image Embeddingcited by 1
  27. 2022Learning to Generate Novel Classes for Deep Metric Learningcited by 1
  28. 2022Improving Generalization of Metric Learning via Listwise Self-distillationcited by 1
  29. 2023Robust Calibrate Proxy Loss for Deep Metric Learningcited by 1
  30. 2023Deep Metric Learning with Soft Orthogonal Proxiescited by 1
  31. 2023Generalized Sum Pooling for Metric Learningcited by 1
  32. 2024Multi-threshold Deep Metric Learning for Facial Expression Recognitioncited by 1
  33. 2024GlobalMamba: Global Image Serialization for Vision Mambacited by 1
  34. 2021IDEAL: Independent Domain Embedding Augmentation Learningcited by 0
  35. 2021Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrixcited by 0
  36. 2022Introspective Deep Metric Learning for Image Retrievalcited by 0
  37. 2022Attention-based Dynamic Subspace Learners for Medical Image Analysiscited by 0
  38. 2022Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoisingcited by 0

50 most cited of 56 All 56 (JSON)