Incremental Learning from Low-labelled Stream Data in Open-Set Video Face Recognition
Use este enlace para citar
http://hdl.handle.net/2183/31524
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución-NoComercial-SinDerivadas 3.0 España
Colecciones
- GI-GAC - Artigos [193]
Metadatos
Mostrar el registro completo del ítemTítulo
Incremental Learning from Low-labelled Stream Data in Open-Set Video Face RecognitionFecha
2022Cita bibliográfica
LOPEZ-LOPEZ, Eric, PARDO, Xose M. and REGUEIRO, Carlos V., 2022. Incremental Learning from Low-labelled Stream Data in Open-Set Video Face Recognition. Pattern Recognition. 1 November 2022. Vol. 131, p. 108885. DOI 10.1016/j.patcog.2022.108885
Resumen
[Abstract] Deep Learning approaches have brought solutions, with impressive performance, to general classification problems where wealthy of annotated data are provided for training. In contrast, less progress has been made in continual learning of a set of non-stationary classes, mainly when applied to unsupervised problems with streaming data.
Here, we propose a novel incremental learning approach which combines a deep features encoder with an Open-Set Dynamic Ensembles of SVM, to tackle the problem of identifying individuals of interest (IoI) from streaming face data. From a simple weak classifier trained on a few video-frames, our method can use unsupervised operational data to enhance recognition. Our approach adapts to new patterns avoiding catastrophic forgetting and partially heals itself from miss-adaptation. Besides, to better comply with real world conditions, the system was designed to operate in an open-set setting. Results show a benefit of up to 15% F1-score increase respect to non-adaptive state-of-the-art methods.
Palabras clave
Open-set face recognition
Incremental Learning
Self-updating
Adaptive biometrics
Video-surveillance
Incremental Learning
Self-updating
Adaptive biometrics
Video-surveillance
Versión del editor
Derechos
Atribución-NoComercial-SinDerivadas 3.0 España