# Triplet Distillation for Deep Face Recognition

arXiv: https://arxiv.org/abs/1905.04457 · HTML: https://mlsanity.com/paper/1905.04457/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2019.

## Built on by (most cited first, 17 of 17)

- [Self-restrained Triplet Loss for Accurate Masked Face Recognition](https://mlsanity.com/paper/2103.01716/) (2021)
- [Evaluation-oriented Knowledge Distillation for Deep Face Recognition](https://mlsanity.com/paper/2206.02325/) (2022)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion](https://mlsanity.com/paper/2111.10561/) (2021)
- [CoupleFace: Relation Matters for Face Recognition Distillation](https://mlsanity.com/paper/2204.05502/) (2022)
- [AdaDistill: Adaptive Knowledge Distillation for Deep Face Recognition](https://mlsanity.com/paper/2407.01332/) (2024)
- [Octuplet Loss: Make Face Recognition Robust to Image Resolution](https://mlsanity.com/paper/2207.06726/) (2022)
- [Grouped Knowledge Distillation for Deep Face Recognition](https://mlsanity.com/paper/2304.04462/) (2023)
- [Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning](https://mlsanity.com/paper/2311.13934/) (2023)
- [Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation](https://mlsanity.com/paper/2211.15597/) (2022)
- [Expanding Knowledge Graphs with Humans in the Loop](https://mlsanity.com/paper/2212.05189/) (2022)
- [Attention-guided Feature Distillation for Semantic Segmentation](https://mlsanity.com/paper/2403.05451/) (2024)
- [AICSD: Adaptive Inter-Class Similarity Distillation for Semantic Segmentation](https://mlsanity.com/paper/2308.04243/) (2023)
- [Learning Using Generated Privileged Information by Text-to-Image Diffusion Models](https://mlsanity.com/paper/2309.15238/) (2023)
- [Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainability](https://mlsanity.com/paper/2504.16056/) (2025)
- [Self Regulated Learning Mechanism for Data Efficient Knowledge Distillation](https://mlsanity.com/paper/2102.07125/) (2021)
- [Confidence Conditioned Knowledge Distillation](https://mlsanity.com/paper/2107.06993/) (2021)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have achieved a great success in face recognition, which unfortunately comes at the cost of massive computation and storage consumption. Many compact face recognition networks are thus proposed to resolve this problem. Triplet loss is effective to further improve the performance of those compact models. However, it normally employs a fixed margin to all the samples, which neglects the informative similarity structures between different identities. In this paper, we propose an enhanced version of triplet loss, named triplet distillation, which exploits the capability of a teacher model to transfer the similarity information to a small model by adaptively varying the margin between positive and negative pairs. Experiments on LFW, AgeDB, and CPLFW datasets show the merits of our method compared to the original triplet loss.