# In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation

arXiv: https://arxiv.org/abs/1912.07863 · HTML: https://mlsanity.com/paper/1912.07863/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2019.

## Built on by (most cited first, 30 of 34)

- [PLIP: Language-Image Pre-training for Person Representation Learning](https://mlsanity.com/paper/2305.08386/) (2023)
- [Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments](https://mlsanity.com/paper/2201.09201/) (2022)
- [On the Unreasonable Effectiveness of Centroids in Image Retrieval](https://mlsanity.com/paper/2104.13643/) (2021)
- [Large-Scale Pre-training for Person Re-identification with Noisy Labels](https://mlsanity.com/paper/2203.16533/) (2022)
- [Deep Learning for Iris Recognition: A Survey](https://mlsanity.com/paper/2210.05866/) (2022)
- [Towards Quantifiable Dialogue Coherence Evaluation](https://mlsanity.com/paper/2106.00507/) (2021)
- [Adaptive Sparse Pairwise Loss for Object Re-Identification](https://mlsanity.com/paper/2303.18247/) (2023)
- [MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2110.11264/) (2021)
- [IRGen: Generative Modeling for Image Retrieval](https://mlsanity.com/paper/2303.10126/) (2023)
- [ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models](https://mlsanity.com/paper/2502.19958/) (2025)
- [Physical Adversarial Attacks for Surveillance: A Survey](https://mlsanity.com/paper/2305.01074/) (2023)
- [Open-Set Biometrics: Beyond Good Closed-Set Models](https://mlsanity.com/paper/2407.16133/) (2024)
- [Disentangling Semantic-to-visual Confusion for Zero-shot Learning](https://mlsanity.com/paper/2106.08605/) (2021)
- [N-pad : Neighboring Pixel-based Industrial Anomaly Detection](https://mlsanity.com/paper/2210.08768/) (2022)
- [Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning](https://mlsanity.com/paper/2309.11082/) (2023)
- [A Comprehensive Survey on Deep-Learning-based Vehicle Re-Identification: Models, Data Sets and Challenges](https://mlsanity.com/paper/2401.10643/) (2024)
- [My Eyes Are Up Here: Promoting Focus on Uncovered Regions in Masked Face Recognition](https://mlsanity.com/paper/2108.00996/) (2021)
- [Sports Re-ID: Improving Re-Identification Of Players In Broadcast Videos Of Team Sports](https://mlsanity.com/paper/2206.02373/) (2022)
- [Camera-aware Label Refinement for Unsupervised Person Re-identification](https://mlsanity.com/paper/2403.16450/) (2024)
- [AdaTriplet: Adaptive Gradient Triplet Loss with Automatic Margin Learning for Forensic Medical Image Matching](https://mlsanity.com/paper/2205.02849/) (2022)
- [LDTrack: Dynamic People Tracking by Service Robots using Diffusion Models](https://mlsanity.com/paper/2402.08774/) (2024)
- [Memory Regulation and Alignment toward Generalizer RGB-Infrared Person](https://mlsanity.com/paper/2109.08843/) (2021)
- [STIR: Siamese Transformer for Image Retrieval Postprocessing](https://mlsanity.com/paper/2304.13393/) (2023)
- [End-to-end multi-modal product matching in fashion e-commerce](https://mlsanity.com/paper/2403.11593/) (2024)
- [Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identification](https://mlsanity.com/paper/2412.10091/) (2024)
- [What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?](https://mlsanity.com/paper/2505.22850/) (2025)
- [E^2TAD: An Energy-Efficient Tracking-based Action Detector](https://mlsanity.com/paper/2204.04416/) (2022)
- [AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2211.08894/) (2022)
- [Rejoining fragmented ancient bamboo slips with physics-driven deep learning](https://mlsanity.com/paper/2505.08601/) (2025)
- [Dynamic Graph Structure Learning via Resistance Curvature Flow](https://mlsanity.com/paper/2601.08149/) (2026)

## Abstract (arXiv)

The comparative losses (typically, triplet loss) are appealing choices for learning person re-identification (ReID) features. However, the triplet loss is computationally much more expensive than the (practically more popular) classification loss, limiting their wider usage in massive datasets. Moreover, the abundance of label noise and outliers in ReID datasets may also put the margin-based loss in jeopardy. This work addresses the above two shortcomings of triplet loss, extending its effectiveness to large-scale ReID datasets with potentially noisy labels. We propose a fast-approximated triplet (FAT) loss, which provably converts the point-wise triplet loss into its upper bound form, consisting of a point-to-set loss term plus cluster compactness regularization. It preserves the effectiveness of triplet loss, while leading to linear complexity to the training set size. A label distillation strategy is further designed to learn refined soft-labels in place of the potentially noisy labels, from only an identified subset of confident examples, through teacher-student networks. We conduct extensive experiments on three most popular ReID benchmarks (Market-1501, DukeMTMC-reID, and MSMT17), and demonstrate that FAT loss with distilled labels lead to ReID features with remarkable accuracy, efficiency, robustness, and direct transferability to unseen datasets.