arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.08054cs.CVcs.AIcs.LG
收藏

多任务学习中的多注释三元组损失用于改进目标检测

Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection

University of Florida(佛罗里达大学);Department of Electrical and Computer Engineering(电气与计算机工程系);Department of Computer and Information Science and Engineering(计算机与信息科学与工程系)

Meilun Zhou, Aditya Dutt, Alina Zare

AI总结:

本文提出多注释三元组损失框架,通过整合额外注释信息提升多任务学习中目标检测的性能。

摘要:

传统三元组损失仅依赖类别标签,而在多个注释类型可用的多任务场景中未利用所有可用信息。本文介绍了一种多注释三元组损失(MATL)框架,通过在损失公式中结合额外注释(如边界框信息)以及类别标签来扩展三元组损失。通过使用这些互补注释,MATL提高了需要分类和定位的任务的多任务学习性能。在航空野生动物图像数据集上的实验表明,MATL在分类和定位方面均优于传统三元组损失。这些发现突显了在多任务学习框架中使用所有可用注释对三元组损失的好处。

英文摘要:

Triplet loss traditionally relies only on class labels and does not use all available information in multi-task scenarios where multiple types of annotations are available. This paper introduces a Multi-Annotation Triplet Loss (MATL) framework that extends triplet loss by incorporating additional annotations, such as bounding box information, alongside class labels in the loss formulation. By using these complementary annotations, MATL improves multi-task learning for tasks requiring both classification and localization. Experiments on an aerial wildlife imagery dataset demonstrate that MATL outperforms conventional triplet loss in both classification and localization. These findings highlight the benefit of using all available annotations for triplet loss in multi-task learning frameworks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑