188 citations · 215 across the 5 of their papers we have counts for
6 papers
PLaMo 2.1-VL Technical Report
Tommi Kerola, Yuya Masuda, Takashi Masuko +5
We introduce PLaMo 2.1-VL, a lightweight Vision Language Model (VLM) for autonomous devices, available in 8B and 2B variants and designed for local and edge deployment with Japanes…
CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers
Yoshihiro Yamada
Transformers have driven remarkable breakthroughs in natural language processing and computer vision, yet their standard attention mechanism still imposes O(N^2) complexity, hinder…
Joint Search of Data Augmentation Policies and Network Architectures
Taiga Kashima, Yoshihiro Yamada, Shunta Saito
The common pipeline of training deep neural networks consists of several building blocks such as data augmentation and network architecture selection. AutoML is a research field th…
Self-supervised Deep Learning for Reading Activity Classification
Md. Rabiul Islam, Shuji Sakamoto, Yoshihiro Yamada +4
Reading analysis can give important information about a user's confidence and habits and can be used to construct feedback to improve a user's reading behavior. A lack of labeled d…
ShakeDrop Regularization for Deep Residual Learning
Yoshihiro Yamada, Masakazu Iwamura, Takuya Akiba +1
Overfitting is a crucial problem in deep neural networks, even in the latest network architectures. In this paper, to relieve the overfitting effect of ResNet and its improvements…
Deep Pyramidal Residual Networks with Separated Stochastic Depth
Yoshihiro Yamada, Masakazu Iwamura, Koichi Kise
On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy. In particular, ResNet and its improvements have broken the lowest error rate record…