Weakly supervised learning based on hypergraph manifold ranking

• Autor(a) principal: Presotto, João Gabriel Camacho [UNESP]
• Data de Publicação: 2022
• Outros Autores: dos Santos, Samuel Felipe, Valem, Lucas Pascotti [UNESP], Faria, Fabio Augusto, Papa, João Paulo [UNESP], Almeida, Jurandy, Pedronette, Daniel Carlos Guimarães [UNESP]
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1016/j.jvcir.2022.103666; http://hdl.handle.net/11449/249306
• topic: Hypergraph; Manifold learning; Ranking; Weakly supervised learning

Significant challenges still remain despite the impressive recent advances in machine learning techniques, particularly in multimedia data understanding. One of the main challenges in real-world scenarios is the nature and relation between training and test datasets. Very often, only small sets of coarse-grained labeled data are available to train models, which are expected to be applied on large datasets and fine-grained tasks. Weakly supervised learning approaches handle such constraints by maximizing useful training information in labeled and unlabeled data. In this research direction, we propose a weakly supervised approach that analyzes the dataset manifold to expand the available labeled set. A hypergraph manifold ranking algorithm is exploited to represent the contextual similarity information encoded in the unlabeled data and identify strong similarity relations, which are taken as a path to label expansion. The expanded labeled set is subsequently exploited for a more comprehensive and accurate training process. The proposed model was evaluated jointly with supervised and semi-supervised classifiers, including Graph Convolutional Networks. The experimental results on image and video datasets demonstrate significant gains and accurate results for different classifiers in diverse scenarios.