BIBLIOS

Tipo
Artigos em Revista

Tipo de Documento
Artigo Completo

Título
Annotate Smarter, Not Harder: Using Active Learning to Reduce Emotional Annotation Effort

Participantes na publicação
Soraia M. Alarcão (Author)
Dep. Informática
Vânia Mendonça (Author)
Dep. Informática
Dep. Informática
LASIGE
Cláudia Sevivas (Author)
Carolina Maruta (Author)
Manuel J. Fonseca (Author)
Dep. Informática
LASIGE

Resumo
The success of supervised models for emotion recognition on images heavily depends on the availability of images properly annotated. Although millions of images are presently available, only a few are annotated with reliable emotional information. Current emotion recognition solutions either use large amounts of weakly-labeled web images, which often contain noise that is unrelated to the emotions of the image, or transfer learning, which usually results in performance losses. Thus, it would be desirable to know which images would be useful to be annotated to avoid an extensive annotation effort. In this paper, we propose a novel approach based on active learning to choose which images are more relevant to be annotated. Our approach dynamically combines multiple active learning strategies and learns the best ones (without prior knowledge of the best ones). Experiments using nine benchmark datasets revealed that: (i) active learning allows to reduce the annotation effort, while reaching or surpassing the performance of a supervised baseline with as little as 3% to 18% of the baseline's training set, in classification tasks; (ii) our online combination of multiple strategies converges to the performance of the best individual strategies, while avoiding the experimentation overhead needed to identify them.


Suporte
IEEE Transactions on Affective Computing

Identificadores da Publicação
ISSN - 1949-3045

Editora
Institute of Electrical and Electronics Engineers (IEEE)


Identificadores do Documento
DOI - https://doi.org/10.1109/taffc.2023.3329563
URL - http://dx.doi.org/10.1109/taffc.2023.3329563

Identificadores de Qualidade
SCIMAGO Q1 (2022) - 1.905 - Human-Computer Interaction