mlsanityData to 14 Oct 2026

FastCAR: Fast Classification And Regression for Task Consolidation in Multi-Task Learning to Model a Continuous Property Variable of Detected Object Class

arXiv 2506.00208 ↗First posted 30 May 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 47 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

23 of 47 references.

References · 23

  1. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  2. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  3. 2017A Survey on Multi-Task Learningcited by 840
  4. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  5. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  6. 2018End-to-End Multi-Task Learning with Attentioncited by 534
  7. 2016Cross-stitch Networks for Multi-task Learningcited by 467
  8. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
  9. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 409
  10. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 222
  11. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  12. 2022Multi-Task Learning as a Bargaining Gamecited by 215
11 more
  1. 2020Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropoutcited by 201
  2. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  3. 2020Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Modelscited by 169
  4. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 151
  5. 2020Learning to Branch for Multi-Task Learningcited by 115
  6. 2021Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learningcited by 101
  7. 2023Independent Component Alignment for Multi-Task Learningcited by 70
  8. 2019MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learningcited by 45
  9. 2023Dual-Balancing for Multi-Task Learningcited by 27
  10. 2018Evolutionary Neural Architecture Search for Image Restorationcited by 12
  11. 2024Low-Latency Task-Oriented Communications with Multi-Round, Multi-Task Deep Learningcited by 2

Built on by

Not cited yet.