BIBLIOS

   Ciências References Management System

Visitor Mode (Login)
Need help?


Back

Publication details

Document type
Journal articles

Document subtype
Full paper

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

Participants in the publication
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
Summary
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.

Date of Publication
2023-11-02

Where published
IEEE Transactions on Affective Computing

Publication Identifiers
ISSN - 1949-3045

Publisher
Institute of Electrical and Electronics Engineers (IEEE)

Number of pages
14
Starting page
1
Last page
14

Document Identifiers
DOI - https://doi.org/10.1109/taffc.2023.3329563
URL - http://dx.doi.org/10.1109/taffc.2023.3329563

Rankings
SCIMAGO Q1 (2022) - 1.905 - Human-Computer Interaction


Export

APA
Soraia M. Alarcão, Vânia Mendonça, Cláudia Sevivas, Carolina Maruta, Manuel J. Fonseca, (2023). Annotate Smarter, Not Harder: Using Active Learning to Reduce Emotional Annotation Effort. IEEE Transactions on Affective Computing, 1-14. ISSN 1949-3045. eISSN . http://dx.doi.org/10.1109/taffc.2023.3329563

IEEE
Soraia M. Alarcão, Vânia Mendonça, Cláudia Sevivas, Carolina Maruta, Manuel J. Fonseca, "Annotate Smarter, Not Harder: Using Active Learning to Reduce Emotional Annotation Effort" in IEEE Transactions on Affective Computing, pp. 1-14, 2023. 10.1109/taffc.2023.3329563

BIBTEX
@article{59656, author = {Soraia M. Alarcão and Vânia Mendonça and Cláudia Sevivas and Carolina Maruta and Manuel J. Fonseca}, title = {Annotate Smarter, Not Harder: Using Active Learning to Reduce Emotional Annotation Effort}, journal = {IEEE Transactions on Affective Computing}, year = 2023, pages = {1-14}, }