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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Meilun, Dutt, Aditya, Zare, Alina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912812887965696
author Zhou, Meilun
Dutt, Aditya
Zare, Alina
author_facet Zhou, Meilun
Dutt, Aditya
Zare, Alina
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08054
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection
Zhou, Meilun
Dutt, Aditya
Zare, Alina
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.08054