Zobrazeno 1 - 10
of 108
pro vyhledávání: '"Guan, Naiyang"'
Vision Transformer (ViT) models have recently emerged as powerful and versatile models for various visual tasks. Recently, a work called PMF has achieved promising results in few-shot image classification by utilizing pre-trained vision transformer m
Externí odkaz:
http://arxiv.org/abs/2309.09276
Few-shot classification aims to adapt to new tasks with limited labeled examples. To fully use the accessible data, recent methods explore suitable measures for the similarity between the query and support images and better high-dimensional features
Externí odkaz:
http://arxiv.org/abs/2307.01515
Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks. However, it is still highly challenging to fully fine-tune these models for downstream tasks due to their high computational and storage costs
Externí odkaz:
http://arxiv.org/abs/2304.13639
Autor:
Qiu, Chunping, Zhang, Xiaoyu, Tong, Xiaochong, Guan, Naiyang, Yi, Xiaodong, Yang, Ke, Zhu, Junjie, Yu, Anzhu
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing March 2024 209:368-382
Publikováno v:
In International Journal of Applied Earth Observation and Geoinformation September 2023 123
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE T-PAMI), vol. 41, no. 1, pp. 246-259, Jan. 2019
Non-negative matrix factorization (NMF) minimizes the Euclidean distance between the data matrix and its low rank approximation, and it fails when applied to corrupted data because the loss function is sensitive to outliers. In this paper, we propose
Externí odkaz:
http://arxiv.org/abs/1906.00495
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Knowledge-Based Systems 15 November 2019 184
Non-negative matrix factorization (NMF) approximates a non-negative matrix $X$ by a product of two non-negative low-rank factor matrices $W$ and $H$. NMF and its extensions minimize either the Kullback-Leibler divergence or the Euclidean distance bet
Externí odkaz:
http://arxiv.org/abs/1207.3438
Publikováno v:
In Neurocomputing 5 September 2016 204:162-171