Saved in:
Bibliographic Details
Main Authors: Kini, Anoop, Jansche, Andreas, Bernthaler, Timo, Schneider, Gerhard
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.00208
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910977892548608
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 the non-triviality of task heterogeneity with only a subtle correlation. The approach addresses the classification of a detected object (occupying the entire image frame) and regression for modeling a continuous property variable (for instances of an object class), a crucial use case in science and engineering. FastCAR involves a label transformation approach that is amenable for use with only a single-task regression network architecture. FastCAR outperforms traditional MTL model families, parametrized in the landscape of architecture and loss weighting schemes, when learning both tasks are collectively considered (classification accuracy of 99.54%, regression mean absolute percentage error of 2.4%). The experiments performed used "Advanced Steel Property Dataset" contributed by us https://github.com/fastcandr/AdvancedSteel-Property-Dataset. The dataset comprises 4536 images of 224x224 pixels, annotated with discrete object classes and its hardness property that can take continuous values. Our proposed FastCAR approach for task consolidation achieves training time efficiency (2.52x quicker) and reduced inference latency (55% faster) than benchmark MTL networks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FastCAR: Fast Classification And Regression for Task Consolidation in Multi-Task Learning to Model a Continuous Property Variable of Detected Object Class
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 the non-triviality of task heterogeneity with only a subtle correlation. The approach addresses the classification of a detected object (occupying the entire image frame) and regression for modeling a continuous property variable (for instances of an object class), a crucial use case in science and engineering. FastCAR involves a label transformation approach that is amenable for use with only a single-task regression network architecture. FastCAR outperforms traditional MTL model families, parametrized in the landscape of architecture and loss weighting schemes, when learning both tasks are collectively considered (classification accuracy of 99.54%, regression mean absolute percentage error of 2.4%). The experiments performed used "Advanced Steel Property Dataset" contributed by us https://github.com/fastcandr/AdvancedSteel-Property-Dataset. The dataset comprises 4536 images of 224x224 pixels, annotated with discrete object classes and its hardness property that can take continuous values. Our proposed FastCAR approach for task consolidation achieves training time efficiency (2.52x quicker) and reduced inference latency (55% faster) than benchmark MTL networks.
title FastCAR: Fast Classification And Regression for Task Consolidation in Multi-Task Learning to Model a Continuous Property Variable of Detected Object Class
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.00208