FastCAR: Fast Classification And Regression Multi-Task Learning via Task Consolidation for Modelling a Continuous Property Variable of Object Classes

arXiv:2403.17926v1 Announce Type: new
Abstract: FastCAR is a novel task consolidation approach in Multi-Task Learning (MTL) for a classification and a regression task, despite task heterogeneity with only subtle correlation. It addresses object classification and continuous property variable regression, a crucial use case in science and engineering. FastCAR involves a labeling transformation approach that can be used with a single-task regression network architecture. FastCAR outperforms traditional MTL model families, parametrized in the landscape of architecture and loss weighting schemes, when …

abstract arxiv classification consolidation continuous correlation cs.cv modelling multi-task learning novel object property regression type via