Weakly supervised learning based on hypergraph manifold ranking?

Author(s)

Presotto, Joao Gabriel Camacho ; dos Santos, Samuel Felipe ; Valem, Lucas Pascotti ; Faria, Fabio Augusto ; Papa, Joao Paulo ; Almeida, Jurandy ; Pedronette, Daniel Carlos Guimaraes

• Document type: Journal article
• Source: JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION; v. 89, p. 12-pg., 2022-10-25.

Abstract

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. (AU)

• FAPESP's process: 18/15597-6 - Aplication and investigation of unsupervised learning methods in retrieval and classification tasks
• Grantee: Daniel Carlos Guimarães Pedronette
• Support Opportunities: Research Grants - Young Investigators Grants - Phase 2
• FAPESP's process: 18/23908-1 - Towards the Robustness in Deep Learning Architectures for e-Science Applications
• Grantee: Fabio Augusto Faria
• Support Opportunities: Scholarships abroad - Research
• FAPESP's process: 17/25908-6 - Weakly supervised learning for compressed video analysis on retrieval and classification tasks for visual alert
• Grantee: João Paulo Papa
• Support Opportunities: Research Grants - Research Partnership for Technological Innovation - PITE
• FAPESP's process: 19/04754-6 - Weakly supervised learning strategies through Rank-based measures
• Grantee: João Gabriel Camacho Presotto
• Support Opportunities: Scholarships in Brazil - Master
• FAPESP's process: 20/11366-0 - Support for computational environments and experiments execution: weakly-supervised and classification fusion methods
• Grantee: Lucas Pascotti Valem
• Support Opportunities: Scholarships in Brazil - Technical Training Program - Technical Training