# Learning Deep Features via Congenerous Cosine Loss for Person Recognition

arXiv: https://arxiv.org/abs/1702.06890 · HTML: https://mlsanity.com/paper/1702.06890/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2017.

## Built on by (most cited first, 7 of 7)

- [Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition](https://mlsanity.com/paper/2109.07270/) (2021)
- [SphereFace2: Binary Classification is All You Need for Deep Face Recognition](https://mlsanity.com/paper/2108.01513/) (2021)
- [Regular Polytope Networks](https://mlsanity.com/paper/2103.15632/) (2021)
- [Recent Advances in Deep Learning Techniques for Face Recognition](https://mlsanity.com/paper/2103.10492/) (2021)
- [Maximally Compact and Separated Features with Regular Polytope Networks](https://mlsanity.com/paper/2301.06116/) (2023)
- [GiMeFive: Towards Interpretable Facial Emotion Classification](https://mlsanity.com/paper/2402.15662/) (2024)
- [Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones](https://mlsanity.com/paper/2101.09412/) (2021)

## Abstract (arXiv)

Person recognition aims at recognizing the same identity across time and space with complicated scenes and similar appearance. In this paper, we propose a novel method to address this task by training a network to obtain robust and representative features. The intuition is that we directly compare and optimize the cosine distance between two features - enlarging inter-class distinction as well as alleviating inner-class variance. We propose a congenerous cosine loss by minimizing the cosine distance between samples and their cluster centroid in a cooperative way. Such a design reduces the complexity and could be implemented via softmax with normalized inputs. Our method also differs from previous work in person recognition that we do not conduct a second training on the test subset. The identity of a person is determined by measuring the similarity from several body regions in the reference set. Experimental results show that the proposed approach achieves better classification accuracy against previous state-of-the-arts.