Salvato in:
Dettagli Bibliografici
Autori principali: Song, Dan, Huo, Shumeng, Li, Wenhui, Wang, Lanjun, Xue, Chao, Liu, An-An
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2501.15503
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917074529419264
author Song, Dan
Huo, Shumeng
Li, Wenhui
Wang, Lanjun
Xue, Chao
Liu, An-An
author_facet Song, Dan
Huo, Shumeng
Li, Wenhui
Wang, Lanjun
Xue, Chao
Liu, An-An
contents The classification and recognition of maritime objects are crucial for enhancing maritime safety, monitoring, and intelligent sea environment prediction. However, existing unsupervised methods for maritime object classification often struggle with the long-tail data distributions in both object categories and weather conditions. In this paper, we construct a dataset named AIMO produced by large-scale generative models with diverse weather conditions and balanced object categories, and collect a dataset named RMO with real-world images where long-tail issue exists. We propose a novel domain adaptation approach that leverages AIMO (source domain) to address the problem of limited labeled data, unbalanced distribution and domain shift in RMO (target domain), enhance the generalization of source features with the Vision-Language Models such as CLIP, and propose a difficulty score for curriculum learning to optimize training process. Experimental results shows that the proposed method significantly improves the classification accuracy, particularly for samples within rare object categories and weather conditions. Datasets and codes will be publicly available at https://github.com/honoria0204/AIMO.
format Preprint
id arxiv_https___arxiv_org_abs_2501_15503
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Domain Adaptation from Generated Multi-Weather Images for Unsupervised Maritime Object Classification
Song, Dan
Huo, Shumeng
Li, Wenhui
Wang, Lanjun
Xue, Chao
Liu, An-An
Computer Vision and Pattern Recognition
The classification and recognition of maritime objects are crucial for enhancing maritime safety, monitoring, and intelligent sea environment prediction. However, existing unsupervised methods for maritime object classification often struggle with the long-tail data distributions in both object categories and weather conditions. In this paper, we construct a dataset named AIMO produced by large-scale generative models with diverse weather conditions and balanced object categories, and collect a dataset named RMO with real-world images where long-tail issue exists. We propose a novel domain adaptation approach that leverages AIMO (source domain) to address the problem of limited labeled data, unbalanced distribution and domain shift in RMO (target domain), enhance the generalization of source features with the Vision-Language Models such as CLIP, and propose a difficulty score for curriculum learning to optimize training process. Experimental results shows that the proposed method significantly improves the classification accuracy, particularly for samples within rare object categories and weather conditions. Datasets and codes will be publicly available at https://github.com/honoria0204/AIMO.
title Domain Adaptation from Generated Multi-Weather Images for Unsupervised Maritime Object Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.15503