# Unsupervised Incremental Learning of Deep Descriptors From Video Streams

arXiv: https://arxiv.org/abs/1708.03615 · HTML: https://mlsanity.com/paper/1708.03615/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2017.

## Built on by (most cited first, 2 of 2)

- [Regular Polytope Networks](https://mlsanity.com/paper/2103.15632/) (2021)
- [Fine-Grained Adversarial Semi-supervised Learning](https://mlsanity.com/paper/2110.05848/) (2021)

## Abstract (arXiv)

We present a novel unsupervised method for face identity learning from video sequences. The method exploits the ResNet deep network for face detection and VGGface fc7 face descriptors together with a smart learning mechanism that exploits the temporal coherence of visual data in video streams. We present a novel feature matching solution based on Reverse Nearest Neighbour and a feature forgetting strategy that supports incremental learning with memory size control, while time progresses. It is shown that the proposed learning procedure is asymptotically stable and can be effectively applied to relevant applications like multiple face tracking.