Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Su, Xingzhe"'
Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of meta-learning
Externí odkaz:
http://arxiv.org/abs/2307.08924
In recent years, self-supervised learning (SSL) has emerged as a promising approach for extracting valuable representations from unlabeled data. One successful SSL method is contrastive learning, which aims to bring positive examples closer while pus
Externí odkaz:
http://arxiv.org/abs/2307.08913
Diffusion Models are a potent class of generative models capable of producing high-quality images. However, they often inadvertently favor certain data attributes, undermining the diversity of generated images. This issue is starkly apparent in skewe
Externí odkaz:
http://arxiv.org/abs/2307.08199
Autor:
Su, Xingzhe, Zheng, Changwen, Qiang, Wenwen, Wu, Fengge, Zhao, Junsuo, Sun, Fuchun, Xiong, Hui
Generative Adversarial Networks (GANs) have shown notable accomplishments in remote sensing domain. However, this paper reveals that their performance on remote sensing images falls short when compared to their impressive results with natural images.
Externí odkaz:
http://arxiv.org/abs/2305.19507
Generative adversarial networks (GANs) have achieved remarkable progress in the natural image field. However, when applying GANs in the remote sensing (RS) image generation task, an extraordinary phenomenon is observed: the GAN model is more sensitiv
Externí odkaz:
http://arxiv.org/abs/2303.05240
Autor:
Gao, Hang, Li, Jiangmeng, Qiang, Wenwen, Si, Lingyu, Su, Xingzhe, Wu, Fengge, Zheng, Changwen, Sun, Fuchun
Benefiting from the injection of human prior knowledge, graphs, as derived discrete data, are semantically dense so that models can efficiently learn the semantic information from such data. Accordingly, graph neural networks (GNNs) indeed achieve im
Externí odkaz:
http://arxiv.org/abs/2301.08496
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Wang, Jingyao, Song, Zeen, Su, Xingzhe, Si, Lingyu, Dong, Hongwei, Qiang, Wenwen, Zheng, Changwen
Through experiments on various meta-learning methods, task samplers, and few-shot learning tasks, this paper arrives at three conclusions. Firstly, there are no universal task sampling strategies to guarantee the performance of meta-learning models.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80dad6eeed4e72ff730699842b4faeb6
http://arxiv.org/abs/2307.08924
http://arxiv.org/abs/2307.08924
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.