Zobrazeno 1 - 10
of 61
pro vyhledávání: '"Mukuta, Yusuke"'
We propose a simple yet effective pipeline for stylizing a 3D scene, harnessing the power of 2D image diffusion models. Given a NeRF model reconstructed from a set of multi-view images, we perform 3D style transfer by refining the source NeRF model u
Externí odkaz:
http://arxiv.org/abs/2406.13393
In offline reinforcement learning, in-sample learning methods have been widely used to prevent performance degradation caused by evaluating out-of-distribution actions from the dataset. Extreme Q-learning (XQL) employs a loss function based on the as
Externí odkaz:
http://arxiv.org/abs/2406.04896
The success of models operating on tokenized data has led to an increased demand for effective tokenization methods, particularly when applied to vision or auditory tasks, which inherently involve non-discrete data. One of the most popular tokenizati
Externí odkaz:
http://arxiv.org/abs/2403.13015
In deep reinforcement learning, estimating the value function to evaluate the quality of states and actions is essential. The value function is often trained using the least squares method, which implicitly assumes a Gaussian error distribution. Howe
Externí odkaz:
http://arxiv.org/abs/2403.07704
Spiking neural networks (SNNs) have garnered considerable attention owing to their ability to run on neuromorphic devices with super-high speeds and remarkable energy efficiencies. SNNs can be used in conventional neural network-based time- and energ
Externí odkaz:
http://arxiv.org/abs/2312.01742
It is imperative to discern the relationships between multiple time series for accurate forecasting. In particular, for stock prices, components are often divided into groups with the same characteristics, and a model that extracts relationships cons
Externí odkaz:
http://arxiv.org/abs/2305.08073
Autor:
Takahama, Shusuke, Kurose, Yusuke, Mukuta, Yusuke, Abe, Hiroyuki, Yoshizawa, Akihiko, Ushiku, Tetsuo, Fukayama, Masashi, Kitagawa, Masanobu, Kitsuregawa, Masaru, Harada, Tatsuya
Pathological image analysis is an important process for detecting abnormalities such as cancer from cell images. However, since the image size is generally very large, the cost of providing detailed annotations is high, which makes it difficult to ap
Externí odkaz:
http://arxiv.org/abs/2304.03537
Autor:
Mukuta, Yusuke, Harada, Tatsuya
This paper proposes a method to construct pretext tasks for self-supervised learning on group equivariant neural networks. Group equivariant neural networks are the models whose structure is restricted to commute with the transformations on the input
Externí odkaz:
http://arxiv.org/abs/2303.04427
Time-series data analysis is important because numerous real-world tasks such as forecasting weather, electricity consumption, and stock market involve predicting data that vary over time. Time-series data are generally recorded over a long period of
Externí odkaz:
http://arxiv.org/abs/2210.00440
Storytelling has always been vital for human nature. From ancient times, humans have used stories for several objectives including entertainment, advertisement, and education. Various analyses have been conducted by researchers and creators to determ
Externí odkaz:
http://arxiv.org/abs/2205.10967