Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Adachi, Kazuki"'
Autor:
Kanai, Sekitoshi, Ida, Yasutoshi, Adachi, Kazuki, Uchida, Mihiro, Yoshida, Tsukasa, Yamaguchi, Shin'ya
This study investigates a method to evaluate time-series datasets in terms of the performance of deep neural networks (DNNs) with state space models (deep SSMs) trained on the dataset. SSMs have attracted attention as components inside DNNs to addres
Externí odkaz:
http://arxiv.org/abs/2408.16261
Autor:
Enomoto, Shohei, Hasegawa, Naoya, Adachi, Kazuki, Sasaki, Taku, Yamaguchi, Shin'ya, Suzuki, Satoshi, Eda, Takeharu
Deep neural networks have achieved remarkable success in a variety of computer vision applications. However, there is a problem of degrading accuracy when the data distribution shifts between training and testing. As a solution of this problem, Test-
Externí odkaz:
http://arxiv.org/abs/2403.17423
Person re-identification (re-id), which aims to retrieve images of the same person in a given image from a database, is one of the most practical image recognition applications. In the real world, however, the environments that the images are taken f
Externí odkaz:
http://arxiv.org/abs/2403.14114
While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source datasets or
Externí odkaz:
http://arxiv.org/abs/2403.10097
Regularized discrete optimal transport (OT) is a powerful tool to measure the distance between two discrete distributions that have been constructed from data samples on two different domains. While it has a wide range of applications in machine lear
Externí odkaz:
http://arxiv.org/abs/2303.07597
Real-world image recognition systems often face corrupted input images, which cause distribution shifts and degrade the performance of models. These systems often use a single prediction model in a central server and process images sent from various
Externí odkaz:
http://arxiv.org/abs/2204.13263
Autor:
Adachi, Kazuki, Yamaguchi, Shin'ya
Existing image recognition techniques based on convolutional neural networks (CNNs) basically assume that the training and test datasets are sampled from i.i.d distributions. However, this assumption is easily broken in the real world because of the
Externí odkaz:
http://arxiv.org/abs/2202.04237
Autor:
Adachi, Kazuki, Xie, Bin
Publikováno v:
In Systems & Control Letters May 2024 187
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.