# How to Train Triplet Networks with 100K Identities?

arXiv: https://arxiv.org/abs/1709.02940 · HTML: https://mlsanity.com/paper/1709.02940/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2017.

## Built on by (most cited first, 8 of 8)

- [Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification](https://mlsanity.com/paper/2104.01546/) (2021)
- [Business Entity Matching with Siamese Graph Convolutional Networks](https://mlsanity.com/paper/2105.03701/) (2021)
- [Causal Scene BERT: Improving object detection by searching for challenging groups of data](https://mlsanity.com/paper/2202.03651/) (2022)
- [DeepSSN: a deep convolutional neural network to assess spatial scene similarity](https://mlsanity.com/paper/2202.04755/) (2022)
- [Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local Descriptors](https://mlsanity.com/paper/2209.11795/) (2022)
- [Relational Representation Learning Network for Cross-Spectral Image Patch Matching](https://mlsanity.com/paper/2403.11751/) (2024)
- [Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching](https://mlsanity.com/paper/2412.11161/) (2024)
- [Blind Speech Separation and Dereverberation using Neural Beamforming](https://mlsanity.com/paper/2103.13443/) (2021)

## Abstract (arXiv)

Training triplet networks with large-scale data is challenging in face recognition. Due to the number of possible triplets explodes with the number of samples, previous studies adopt the online hard negative mining(OHNM) to handle it. However, as the number of identities becomes extremely large, the training will suffer from bad local minima because effective hard triplets are difficult to be found. To solve the problem, in this paper, we propose training triplet networks with subspace learning, which splits the space of all identities into subspaces consisting of only similar identities. Combined with the batch OHNM, hard triplets can be found much easier. Experiments on the large-scale MS-Celeb-1M challenge with 100K identities demonstrate that the proposed method can largely improve the performance. In addition, to deal with heavy noise and large-scale retrieval, we also make some efforts on robust noise removing and efficient image retrieval, which are used jointly with the subspace learning to obtain the state-of-the-art performance on the MS-Celeb-1M competition (without external data in Challenge1).