# Improved Embeddings with Easy Positive Triplet Mining

arXiv: https://arxiv.org/abs/1904.04370 · HTML: https://mlsanity.com/paper/1904.04370/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 30 of 67)

- [DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers](https://mlsanity.com/paper/2204.12997/) (2022)
- [Learning Intra-Batch Connections for Deep Metric Learning](https://mlsanity.com/paper/2102.07753/) (2021)
- [Non-isotropy Regularization for Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2203.08547/) (2022)
- [Perspectives on individual animal identification from biology and computer vision](https://mlsanity.com/paper/2103.00560/) (2021)
- [It Takes Two to Tango: Mixup for Deep Metric Learning](https://mlsanity.com/paper/2106.04990/) (2021)
- [Deep Relational Metric Learning](https://mlsanity.com/paper/2108.10026/) (2021)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [Integrating Language Guidance into Vision-based Deep Metric Learning](https://mlsanity.com/paper/2203.08543/) (2022)
- [A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning](https://mlsanity.com/paper/2207.03784/) (2022)
- [Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning](https://mlsanity.com/paper/2107.09562/) (2021)
- [Continual Learning for Visual Search with Backward Consistent Feature Embedding](https://mlsanity.com/paper/2205.13384/) (2022)
- [Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey](https://mlsanity.com/paper/2201.09267/) (2022)
- [GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training](https://mlsanity.com/paper/2208.04060/) (2022)
- [Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination](https://mlsanity.com/paper/2308.04380/) (2023)
- [Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval](https://mlsanity.com/paper/2105.03647/) (2021)
- [Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems](https://mlsanity.com/paper/2110.07933/) (2021)
- [Contrastive Bayesian Analysis for Deep Metric Learning](https://mlsanity.com/paper/2210.04402/) (2022)
- [LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning](https://mlsanity.com/paper/2108.09335/) (2021)
- [Introspective Deep Metric Learning](https://mlsanity.com/paper/2309.09982/) (2023)
- [Learning video retrieval models with relevance-aware online mining](https://mlsanity.com/paper/2203.08688/) (2022)
- [The Group Loss++: A deeper look into group loss for deep metric learning](https://mlsanity.com/paper/2204.01509/) (2022)
- [Relevance-based Margin for Contrastively-trained Video Retrieval Models](https://mlsanity.com/paper/2204.13001/) (2022)
- [OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation](https://mlsanity.com/paper/2405.20141/) (2024)
- [Improving Deep Metric Learning by Divide and Conquer](https://mlsanity.com/paper/2109.04003/) (2021)
- [DeepBrainPrint: A Novel Contrastive Framework for Brain MRI Re-Identification](https://mlsanity.com/paper/2302.13057/) (2023)
- [Globally Correlation-Aware Hard Negative Generation](https://mlsanity.com/paper/2411.13145/) (2024)
- [Exploring Adversarial Robustness of Deep Metric Learning](https://mlsanity.com/paper/2102.07265/) (2021)
- [The 2021 Hotel-ID to Combat Human Trafficking Competition Dataset](https://mlsanity.com/paper/2106.05746/) (2021)
- [MovingFashion: a Benchmark for the Video-to-Shop Challenge](https://mlsanity.com/paper/2110.02627/) (2021)
- [TATA: Stance Detection via Topic-Agnostic and Topic-Aware Embeddings](https://mlsanity.com/paper/2310.14450/) (2023)

## Abstract (arXiv)

Deep metric learning seeks to define an embedding where semantically similar images are embedded to nearby locations, and semantically dissimilar images are embedded to distant locations. Substantial work has focused on loss functions and strategies to learn these embeddings by pushing images from the same class as close together in the embedding space as possible. In this paper, we propose an alternative, loosened embedding strategy that requires the embedding function only map each training image to the most similar examples from the same class, an approach we call "Easy Positive" mining. We provide a collection of experiments and visualizations that highlight that this Easy Positive mining leads to embeddings that are more flexible and generalize better to new unseen data. This simple mining strategy yields recall performance that exceeds state of the art approaches (including those with complicated loss functions and ensemble methods) on image retrieval datasets including CUB, Stanford Online Products, In-Shop Clothes and Hotels-50K.