Zobrazeno 1 - 10
of 93
pro vyhledávání: '"Hirakawa, Tsubasa"'
Autor:
Long, Nguyen Huu Bao, Zhang, Chenyu, Shi, Yuzhi, Hirakawa, Tsubasa, Yamashita, Takayoshi, Matsui, Tohgoroh, Fujiyoshi, Hironobu
Publikováno v:
ACCV 2024
Vision Transformers with various attention modules have demonstrated superior performance on vision tasks. While using sparsity-adaptive attention, such as in DAT, has yielded strong results in image classification, the key-value pairs selected by de
Externí odkaz:
http://arxiv.org/abs/2410.08582
Autor:
Komatsu, Takumi, Kambara, Motonari, Hatanaka, Shumpei, Matsuo, Haruka, Hirakawa, Tsubasa, Yamashita, Takayoshi, Fujiyoshi, Hironobu, Sugiura, Komei
Domestic service robots (DSRs) that support people in everyday environments have been widely investigated. However, their ability to predict and describe future risks resulting from their own actions remains insufficient. In this study, we focus on t
Externí odkaz:
http://arxiv.org/abs/2407.13186
Autor:
Otsuki, Seitaro, Iida, Tsumugi, Doublet, Félix, Hirakawa, Tsubasa, Yamashita, Takayoshi, Fujiyoshi, Hironobu, Sugiura, Komei
The transparent formulation of explanation methods is essential for elucidating the predictions of neural networks, which are typically black-box models. Layer-wise Relevance Propagation (LRP) is a well-established method that transparently traces th
Externí odkaz:
http://arxiv.org/abs/2407.09115
Autor:
Itaya, Hidenori, Hirakawa, Tsubasa, Yamashita, Takayoshi, Fujiyoshi, Hironobu, Sugiura, Komei
The excellent performance of Transformer in supervised learning has led to growing interest in its potential application to deep reinforcement learning (DRL) to achieve high performance on a wide variety of problems. However, the decision making of a
Externí odkaz:
http://arxiv.org/abs/2306.13879
Visual explanation is an approach for visualizing the grounds of judgment by deep learning, and it is possible to visually interpret the grounds of a judgment for a certain input by visualizing an attention map. As for deep-learning models that outpu
Externí odkaz:
http://arxiv.org/abs/2306.02257
Autor:
Sumiko Anno, Hirakawa Tsubasa, Satoru Sugita, Shinya Yasumoto, Ming-An Lee, Yoshinobu Sasaki, Kei Oyoshi
Publikováno v:
Geo-spatial Information Science, Vol 27, Iss 4, Pp 1155-1161 (2024)
Ongoing climate change has accelerated the outbreak and expansion of climate-sensitive infectious diseases such as dengue fever. Dengue fever will remain a threat until safe and effective vaccines and antiviral drugs have been developed, distributed,
Externí odkaz:
https://doaj.org/article/c7285f93b871485893216afecdc6bd80
Autor:
Adachi, Hiroki, Hirakawa, Tsubasa, Yamashita, Takayoshi, Fujiyoshi, Hironobu, Ishii, Yasunori, Kozuka, Kazuki
While convolutional neural networks (CNNs) have achieved excellent performances in various computer vision tasks, they often misclassify with malicious samples, a.k.a. adversarial examples. Adversarial training is a popular and straightforward techni
Externí odkaz:
http://arxiv.org/abs/2302.08066
Autor:
Fujii, Shungo, Ishii, Yasunori, Kozuka, Kazuki, Hirakawa, Tsubasa, Yamashita, Takayoshi, Fujiyoshi, Hironobu
Data augmentation is an essential technique for improving recognition accuracy in object recognition using deep learning. Methods that generate mixed data from multiple data sets, such as mixup, can acquire new diversity that is not included in the t
Externí odkaz:
http://arxiv.org/abs/2209.05122
Autor:
Maruyama, Yuya, Fukui, Hiroshi, Hirakawa, Tsubasa, Yamashita, Takayoshi, Fujiyoshi, Hironobu, Sugiura, Komei
Robot navigation with deep reinforcement learning (RL) achieves higher performance and performs well under complex environment. Meanwhile, the interpretation of the decision-making of deep RL models becomes a critical problem for more safety and reli
Externí odkaz:
http://arxiv.org/abs/2208.08613
In this paper we propose an extension of the Attention Branch Network (ABN) by using instance segmentation for generating sharper attention maps for action recognition. Methods for visual explanation such as Grad-CAM usually generate blurry maps whic
Externí odkaz:
http://arxiv.org/abs/2207.13306