Human-in-the-loop: Using classifier decision boundary maps to improve pseudo labels

Autor(es)

Benato, Barbara C. ; Grosu, Cristian ; Falcao, Alexandre X. ; Telea, Alexandru C.

• Tipo de documento: Artigo Científico
• Fonte: COMPUTERS & GRAPHICS-UK; v. 124, p. 13-pg., 2024-09-05.

Resumo

For classification tasks, several strategies aim to tackle the problem of not having sufficient labeled data, usually by automatic labeling or by fully passing this task to a user. Automatic labeling is simple to apply but can fail handling complex situations where human insights maybe required to decide the correct labels. Conversely, manual labeling leverages the expertise of specialists but may waste precious effort which could be handled by automatic methods. More specifically, automatic solutions could be improved by combining an active learning loop with manual labeling assisted by visual depictions of a classifier's behavior. We propose to include the human in the labeling loop by using manual labeling in feature spaces produced by a deep feature annotation (DeepFA) technique. To assist manual labeling, we provide users with visual insights on the classifier's decision boundaries. Finally, we use the manual and automatically computed labels jointly to retrain the classifier in an active learning (AL) loop scheme. Experiments using a toy and a real-world application dataset show that our proposed combination of manual labeling supported by visualization of decision boundaries and automatic labeling can yield a significant increase in classifier performance with a quite limited user effort. (AU)

• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: Francisco Louzada Neto
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 22/12668-5 - Explorando análise visual de dados para auxiliar o usuário no aprendizado ativo
• Beneficiário: Bárbara Caroline Benato
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado
• Processo FAPESP: 19/10705-8 - Aprendizado Ativo Visual guiado por Projeções de Características
• Beneficiário: Bárbara Caroline Benato
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 23/14427-8 - Ciência de Dados para a Indústria Inteligente (CDII)
• Beneficiário: José Alberto Cuminato
• Modalidade de apoio: Auxílio à Pesquisa - Programa Centros de Pesquisa em Engenharia