Learning Person-Specific Representations From Faces in the Wild

Autor(es)

Chiachia, Giovani ^[1] ; Falcao, Alexandre X. ^[1] ; Pinto, Nicolas ^[2] ; Rocha, Anderson ^[1] ; Cox, David ^[2]

Afiliação do(s) autor(es)

^[1] Univ Estadual Campinas, Inst Comp, BR-13083970 Campinas, SP - Brazil

^[2] Harvard Univ, Cambridge, MA 02138 - USA

• Tipo de documento: Artigo Científico
• Fonte: IEEE Transactions on Information Forensics and Security; v. 9, n. 12, p. 2089-2099, DEC 2014.
• Citações Web of Science: 19

Resumo

Humans are natural face recognition experts, far out-performing current automated face recognition algorithms, especially in naturalistic, ``in the wild{''} settings. However, a striking feature of human face recognition is that we are dramatically better at recognizing highly familiar faces, presumably because we can leverage large amounts of past experience with the appearance of an individual to aid future recognition. Meanwhile, the analogous situation in automated face recognition, where a large number of training examples of an individual are available, has been largely underexplored, in spite of the increasing relevance of this setting in the age of social media. Inspired by these observations, we propose to explicitly learn enhanced face representations on a per-individual basis, and we present two methods enabling this approach. By learning and operating within person-specific representations, we are able to significantly outperform the previous state-of-the-art on PubFig83, a challenging benchmark for familiar face recognition in the wild, using a novel method for learning representations in deep visual hierarchies. We suggest that such person-specific representations aid recognition by introducing an intermediate form of regularization to the problem. (AU)

• Processo FAPESP: 10/00994-8 - Aprendendo representações específicas para a face de cada pessoa
• Beneficiário: Giovani Chiachia
• Linha de fomento: Bolsas no Brasil - Doutorado
• Processo FAPESP: 13/11359-0 - Novos métodos para aprendizado de hierarquias visuais profundas
• Beneficiário: Giovani Chiachia
• Linha de fomento: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 10/05647-4 - Computação forense e criminalística de documentos: coleta, organização, classificação e análise de evidências
• Beneficiário: Anderson de Rezende Rocha
• Linha de fomento: Auxílio à Pesquisa - Apoio a Jovens Pesquisadores