# Sampling Matters in Deep Embedding Learning

arXiv: https://arxiv.org/abs/1706.07567 · HTML: https://mlsanity.com/paper/1706.07567/

## Key facts

- Cited by 285 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2017.

## Built on by (most cited first, 30 of 285)

- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Hyperbolic Vision Transformers: Combining Improvements in Metric Learning](https://mlsanity.com/paper/2203.10833/) (2022)
- [Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation](https://mlsanity.com/paper/2303.11851/) (2023)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (2022)
- [Training Vision Transformers for Image Retrieval](https://mlsanity.com/paper/2102.05644/) (2021)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [Verbs in Action: Improving verb understanding in video-language models](https://mlsanity.com/paper/2304.06708/) (2023)
- [Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings](https://mlsanity.com/paper/2202.06671/) (2022)
- [Audio Self-supervised Learning: A Survey](https://mlsanity.com/paper/2203.01205/) (2022)
- [Instance-level Image Retrieval using Reranking Transformers](https://mlsanity.com/paper/2103.12236/) (2021)
- [Yo'LLaVA: Your Personalized Language and Vision Assistant](https://mlsanity.com/paper/2406.09400/) (2024)
- [Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework](https://mlsanity.com/paper/2204.13207/) (2022)
- [Visual Recognition with Deep Nearest Centroids](https://mlsanity.com/paper/2209.07383/) (2022)
- [Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning](https://mlsanity.com/paper/2102.06605/) (2021)
- [Recall@k Surrogate Loss with Large Batches and Similarity Mixup](https://mlsanity.com/paper/2108.11179/) (2021)
- [Towards Robust Bisimulation Metric Learning](https://mlsanity.com/paper/2110.14096/) (2021)
- [Incremental False Negative Detection for Contrastive Learning](https://mlsanity.com/paper/2106.03719/) (2021)
- [LocVTP: Video-Text Pre-training for Temporal Localization](https://mlsanity.com/paper/2207.10362/) (2022)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021)
- [Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding](https://mlsanity.com/paper/2306.08832/) (2023)
- [Towards Unsupervised Domain Generalization](https://mlsanity.com/paper/2107.06219/) (2021)
- [SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding](https://mlsanity.com/paper/2306.05407/) (2023)
- [SAMAug: Point Prompt Augmentation for Segment Anything Model](https://mlsanity.com/paper/2307.01187/) (2023)
- [Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification](https://mlsanity.com/paper/2104.01546/) (2021)
- [Simple, Effective and General: A New Backbone for Cross-view Image Geo-localization](https://mlsanity.com/paper/2302.01572/) (2023)
- [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)
- [Data curation via joint example selection further accelerates multimodal learning](https://mlsanity.com/paper/2406.17711/) (2024)

## Abstract (arXiv)

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network with a suitable loss function, such as contrastive loss or triplet loss. While a rich line of work focuses solely on the loss functions, we show in this paper that selecting training examples plays an equally important role. We propose distance weighted sampling, which selects more informative and stable examples than traditional approaches. In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions. We evaluate our approach on the Stanford Online Products, CAR196, and the CUB200-2011 datasets for image retrieval and clustering, and on the LFW dataset for face verification. Our method achieves state-of-the-art performance on all of them.