Data to 14 Oct 2026

Deep Metric Learning via Lifted Structured Feature Embedding

arXiv 1511.06452 ↗First posted 19 Nov 2015cs.CV cs.LGcited by 449

Not on the map. Why?

Abstract (arXiv)

Learning the distance metric between pairs of examples is of great importance for learning and visual recognition. With the remarkable success from the state of the art convolutional neural networks, recent works have shown promising results on discriminatively training the networks to learn semantic feature embeddings where similar examples are mapped close to each other and dissimilar examples are mapped farther apart. In this paper, we describe an algorithm for taking full advantage of the training batches in the neural network training by lifting the vector of pairwise distances within the batch to the matrix of pairwise distances. This step enables the algorithm to learn the state of the art feature embedding by optimizing a novel structured prediction objective on the lifted problem. Additionally, we collected Online Products dataset: 120k images of 23k classes of online products for metric learning. Our experiments on the CUB-200-2011, CARS196, and Online Products datasets demonstrate significant improvement over existing deep feature embedding methods on all experimented embedding sizes with the GoogLeNet network.

Key facts. Cited by 449 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 114; 2022: 123; 2023: 82; 2024: 66; 2025: 38; 2026: 26.

449 papers.

Sort:

By area:

2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
2023A Cookbook of Self-Supervised Learningcited by 250
2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
2023Hyperbolic Image-Text Representationscited by 136
2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
2022CyCLIP: Cyclic Contrastive Language-Image Pretrainingcited by 127
2022What to Hide from Your Students: Attention-Guided Masked Image Modelingcited by 118
2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 111
2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
2021Training Vision Transformers for Image Retrievalcited by 90

38 more

2023Image Captioners Are Scalable Vision Learners Toocited by 89
2021ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shotcited by 86
2022A Survey on Long-Tailed Visual Recognitioncited by 75
2021Cross Modal Retrieval with Querybank Normalisationcited by 72
2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
2022SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellitecited by 64
2021Instance-level Image Retrieval using Reranking Transformerscited by 63
2021RSG: A Simple but Effective Module for Learning Imbalanced Datasetscited by 61
2022Visual Recognition with Deep Nearest Centroidscited by 59
2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
2021Incremental False Negative Detection for Contrastive Learningcited by 48
2022Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularizationcited by 45
2025Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversioncited by 43
2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
2021Mutual Contrastive Learning for Visual Representation Learningcited by 42
2021SphereFace2: Binary Classification is All You Need for Deep Face Recognitioncited by 42
2022Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learningcited by 38
2021Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Miningcited by 37
2022ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCOcited by 37
2024TIPS: Text-Image Pretraining with Spatial awarenesscited by 37
2022Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognitioncited by 36
2023Unicom: Universal and Compact Representation Learning for Image Retrievalcited by 36
2023Contrastive Difference Predictive Codingcited by 36
2021Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learningcited by 35
2022Understanding Deep Contrastive Learning via Coordinate-wise Optimizationcited by 35
2021Learning Intra-Batch Connections for Deep Metric Learningcited by 34
2023Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentationcited by 34
2022Non-isotropy Regularization for Proxy-based Deep Metric Learningcited by 33
2021GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognitioncited by 31
2021Pairwise Supervised Contrastive Learning of Sentence Representationscited by 31
2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 31
2021Towards Interpretable Deep Metric Learning with Structural Matchingcited by 30
2022Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learningcited by 30
2024AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Modelscited by 30
2024Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Latercited by 30
2025ILIAS: Instance-Level Image retrieval At Scalecited by 30
2023Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representationscited by 28

50 most cited of 449 All 449 (JSON)