Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lê, Hoàng-Ân, Pham, Minh-Tan
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909210010189824
author Lê, Hoàng-Ân
Pham, Minh-Tan
author_facet Lê, Hoàng-Ân
Pham, Minh-Tan
contents Partial multi-task learning where training examples are annotated for one of the target tasks is a promising idea in remote sensing as it allows combining datasets annotated for different tasks and predicting more tasks with fewer network parameters. The naïve approach to partial multi-task learning is sub-optimal due to the lack of all-task annotations for learning joint representations. This paper proposes using knowledge distillation to replace the need of ground truths for the alternate task and enhance the performance of such approach. Experiments conducted on the public ISPRS 2D Semantic Labeling Contest dataset show the effectiveness of the proposed idea on partial multi-task learning for semantic tasks including object detection and semantic segmentation in aerial images.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15394
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets
Lê, Hoàng-Ân
Pham, Minh-Tan
Computer Vision and Pattern Recognition
Partial multi-task learning where training examples are annotated for one of the target tasks is a promising idea in remote sensing as it allows combining datasets annotated for different tasks and predicting more tasks with fewer network parameters. The naïve approach to partial multi-task learning is sub-optimal due to the lack of all-task annotations for learning joint representations. This paper proposes using knowledge distillation to replace the need of ground truths for the alternate task and enhance the performance of such approach. Experiments conducted on the public ISPRS 2D Semantic Labeling Contest dataset show the effectiveness of the proposed idea on partial multi-task learning for semantic tasks including object detection and semantic segmentation in aerial images.
title Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.15394