Scene designer: compositional sketch-based image retrieval with contrastive learning and an auxiliary synthesis task

Autor(es)

Sampaio Ferraz Ribeiro, Leo ; Bui, Tu ; Collomosse, John ; Ponti, Moacir

• Tipo de documento: Artigo Científico
• Fonte: MULTIMEDIA TOOLS AND APPLICATIONS; v. N/A, p. 23-pg., 2022-12-20.

Resumo

Scene Designer is a novel method for Compositional Sketch-based Image Retrieval (CSBIR) that combines semantic layout synthesis with its main task both to boost performance and enable new creative workflows. While most studies on sketch focus on single-object retrieval, we look to multi-object scenes instead for increased query specificity and flexibility. Our training protocol improves contrastive learning by synthesising harder negative samples and introduces a layout synthesis task that further improves the semantic scene representations. We show that our object-oriented graph neural network (GNN) more than doubles the current SoTA recall@1 on the SketchyCOCO CSBIR benchmark under our novel contrastive learning setting and combined search and synthesis tasks. Furthermore, we introduce the first large-scale sketched scene dataset and benchmark in QuickDrawCOCO. (AU)

• Processo FAPESP: 19/02808-1 - Encontrando correspondências entre representações de diferentes domínios usando combinações de características não-supervisionadas
• Beneficiário: Leo Sampaio Ferraz Ribeiro
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado Direto
• Processo FAPESP: 17/22366-8 - Redes geradoras e aprendizado de características para busca entre domínios visuais
• Beneficiário: Leo Sampaio Ferraz Ribeiro
• Modalidade de apoio: Bolsas no Brasil - Doutorado Direto
• Processo FAPESP: 19/07316-0 - Teoria de singularidades e aplicações a geometria diferencial, equações diferenciais e visão computacional
• Beneficiário: Farid Tari
• Modalidade de apoio: Auxílio à Pesquisa - Temático