FastCAR: Fast Classification And Regression Multi-Task Learning via Task Consolidation for Modelling a Continuous Property Variable of Object Classes
It addresses a crucial use case in science and engineering for modeling continuous property variables of object classes, but it is incremental as it builds on existing multi-task learning methods.
The paper tackles the problem of multi-task learning for classification and regression with heterogeneous tasks by proposing FastCAR, a task consolidation approach that uses labeling transformation with a single-task regression network, achieving 99.54% classification accuracy and 2.4% regression mean absolute percentage error.
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 learning of both tasks are collectively considered (classification accuracy of 99.54\%, regression mean absolute percentage error of 2.4\%). The experiments performed used an Advanced Steel Property dataset https://github.com/fastcandr/Advanced-Steel-Property-Dataset contributed by us. The dataset comprises 4536 images of 224x224 pixels, annotated with object classes and hardness properties that take continuous values. With our designed approach, FastCAR achieves reduced latency and time efficiency.