Saved in:
Bibliographic Details
Main Authors: Kini, Anoop, Jansche, Andreas, Bernthaler, Timo, Schneider, Gerhard
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.17926
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916769497612288
author Kini, Anoop
Jansche, Andreas
Bernthaler, Timo
Schneider, Gerhard
author_facet Kini, Anoop
Jansche, Andreas
Bernthaler, Timo
Schneider, Gerhard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17926
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FastCAR: Fast Classification And Regression Multi-Task Learning via Task Consolidation for Modelling a Continuous Property Variable of Object Classes
Kini, Anoop
Jansche, Andreas
Bernthaler, Timo
Schneider, Gerhard
Computer Vision and Pattern Recognition
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.
title FastCAR: Fast Classification And Regression Multi-Task Learning via Task Consolidation for Modelling a Continuous Property Variable of Object Classes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.17926