Unsupervised incremental learning of deep descriptors from video streams
By Federico Pernici, A. del Bimbo. 2017
12 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Rahaf Aljundi
- Matteo Bruni
- A. del Bimbo
- Federico Pernici
- Claudio Baecchi
- Tinne Tuytelaars
- Joost van de Weijer
- Dacheng Tao
Citations in the corpus
- Task-Free Continual Learning (2018, neutral): “In terms of applications, the work of Pernici et al. [26, 25] is similar to our first application scenario.”
- Regular Polytope Networks (2021, background): “The works [60]–[62] accumulate extracted face features in a memory bank to preserve all the past knowledge without forgetting and at the same time handle the nonstationarity of the data stream.”
- Continual Learning in Neural Networks (2019, result): “[115, 114] is similar to our first application scenario.”