Task-Guided Multi-Annotation Triplet Learning for Remote Sensing Representations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhou, Meilun, Zare, Alina
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915916318507008
author Zhou, Meilun
Zare, Alina
author_facet Zhou, Meilun
Zare, Alina
contents Prior multi-task triplet loss methods relied on static weights to balance supervision between various types of annotation. However, static weighting requires tuning and does not account for how tasks interact when shaping a shared representation. To address this, the proposed task-guided multi-annotation triplet loss removes this dependency by selecting triplets through a mutual-information criteria that identifies triplets most informative across tasks. This strategy modifies which samples influence the representation rather than adjusting loss magnitudes. Experiments on an aerial wildlife dataset compare the proposed task-guided selection against several triplet loss setups for shaping a representation in an effective multi-task manner. The results show improved classification and regression performance and demonstrate that task-aware triplet selection produces a more effective shared representation for downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03837
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Task-Guided Multi-Annotation Triplet Learning for Remote Sensing Representations
Zhou, Meilun
Zare, Alina
Computer Vision and Pattern Recognition
Prior multi-task triplet loss methods relied on static weights to balance supervision between various types of annotation. However, static weighting requires tuning and does not account for how tasks interact when shaping a shared representation. To address this, the proposed task-guided multi-annotation triplet loss removes this dependency by selecting triplets through a mutual-information criteria that identifies triplets most informative across tasks. This strategy modifies which samples influence the representation rather than adjusting loss magnitudes. Experiments on an aerial wildlife dataset compare the proposed task-guided selection against several triplet loss setups for shaping a representation in an effective multi-task manner. The results show improved classification and regression performance and demonstrate that task-aware triplet selection produces a more effective shared representation for downstream tasks.
title Task-Guided Multi-Annotation Triplet Learning for Remote Sensing Representations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.03837