# In Defense of the Triplet Loss for Person Re-Identification

arXiv: https://arxiv.org/abs/1703.07737 · HTML: https://mlsanity.com/paper/1703.07737/

## Key facts

- Cited by 786 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2017.

## Built on by (most cited first, 30 of 786)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Thin-Plate Spline Motion Model for Image Animation](https://mlsanity.com/paper/2203.14367/) (2022)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection](https://mlsanity.com/paper/2103.09096/) (2021)
- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [Clothes-Changing Person Re-identification with RGB Modality Only](https://mlsanity.com/paper/2204.06890/) (2022)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (2022)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [Monocular Quasi-Dense 3D Object Tracking](https://mlsanity.com/paper/2103.07351/) (2021)
- [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis](https://mlsanity.com/paper/2109.05488/) (2021)
- [Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization](https://mlsanity.com/paper/2103.15537/) (2021)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences](https://mlsanity.com/paper/2108.07422/) (2021)
- [Deep Learning for Face Anti-Spoofing: A Survey](https://mlsanity.com/paper/2106.14948/) (2021)
- [DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers](https://mlsanity.com/paper/2204.12997/) (2022)
- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [Nested Collaborative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2203.15359/) (2022)
- [Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search](https://mlsanity.com/paper/2101.03036/) (2021)
- [SiamMOT: Siamese Multi-Object Tracking](https://mlsanity.com/paper/2105.11595/) (2021)
- [QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking](https://mlsanity.com/paper/2210.06984/) (2022)
- [Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification](https://mlsanity.com/paper/2307.15254/) (2023)
- [Part-based Pseudo Label Refinement for Unsupervised Person Re-identification](https://mlsanity.com/paper/2203.14675/) (2022)
- [A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model](https://mlsanity.com/paper/2407.15362/) (2024)
- [GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set](https://mlsanity.com/paper/2102.03247/) (2021)

## Abstract (arXiv)

In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning. The person re-identification subfield is no exception to this. Unfortunately, a prevailing belief in the community seems to be that the triplet loss is inferior to using surrogate losses (classification, verification) followed by a separate metric learning step. We show that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.