no code implementations • 28 Dec 2022 • Huipeng Zheng, Lukman Hakim, Takio Kurita, Junichi Miyao
The deep learning technique was used to increase the performance of single image super-resolution (SISR).
no code implementations • 28 Dec 2022 • Lukman Hakim, Takio Kurita
Using pixel-wise loss neglected the pixel neighbor relationships in the network learning process.
no code implementations • 9 Mar 2022 • Novanto Yudistira, Muthu Subash Kavitha, Jeny Rajan, Takio Kurita
It is designed in a single model to produce weak segmentation and classification of colonies without using finely labeled samples.
no code implementations • 17 Dec 2020 • Novanto Yudistira, Muthu Subash Kavitha, Takio Kurita
The proposed approach intends to show the usefulness of every layer termed as global-local attention in 3D CNN via visual attribution, weakly-supervised action localization, and action recognition.
2 code implementations • 2 Dec 2020 • Motoshi Abe, Junichi Miyao, Takio Kurita
As the one technique of dimensionality reduction, a stochastic neighbor embedding (SNE) was introduced.
no code implementations • 4 Nov 2020 • Kakeru Mitsuno, Yuichiro Nomura, Takio Kurita
Our planting can search the optimal network architecture with smaller number of parameters for improving the network performance by augmenting channels incrementally to layers of the initial networks while keeping the earlier trained parameters fixed.
no code implementations • 4 Nov 2020 • Kakeru Mitsuno, Takio Kurita
It is shown that the proposed method can reduce more than 50% parameters of ResNet for CIFAR-10 with only 0. 3% decrease in the accuracy of test samples.
no code implementations • 24 Sep 2020 • Shah B. Shrey, Lukman Hakim, Muthusubash Kavitha, Hae Won Kim, Takio Kurita
The experimental results showed that the classification accuracy of 97. 96\% of our proposed architecture outperformed other simple and complex architectures in classifying lung nodules for lung cancer detection.
no code implementations • 16 Sep 2020 • Lukman Hakim, Novanto Yudistira, Muthusubash Kavitha, Takio Kurita
The detection of retinal blood vessels, especially the changes of small vessel condition is the most important indicator to identify the vascular network of the human body.
1 code implementation • 17 Apr 2020 • Hideki Oki, Motoshi Abe, Junichi Miyao, Takio Kurita
The functionality of the metric learning to reduce the differences between similar outputs can be used for the knowledge distillation to reduce the differences between the outputs of the teacher model and the student model.
1 code implementation • 17 Apr 2020 • Motoshi Abe, Junichi Miyao, Takio Kurita
The neuron-wise discriminant criterion makes the input feature of each neuron in the output layer discriminative by introducing the discriminant criterion to each of the features.
1 code implementation • 9 Apr 2020 • Kakeru Mitsuno, Junichi Miyao, Takio Kurita
As a result, we can prune the weights more adequately depending on the structure of the network and the number of channels keeping high performance.
no code implementations • 19 Feb 2020 • Zhao Fangda, Toru Tamaki, Takio Kurita, Bisser Raytchev, Kazufumi Kaneda
First, successive images are fed to a PoseNet-based network to obtain ego-motion of cameras between frames.
no code implementations • 24 Jun 2019 • Hideki Oki, Takio Kurita
However, the recognition accuracy of the trained deep CNN drastically decreases for the samples which are obtained from the outside regions of the training samples.
no code implementations • 22 Jul 2018 • Novanto Yudistira, Takio Kurita
The existing fusion approach averages the two streams.
4 code implementations • 18 Jul 2017 • Jin Yamanaka, Shigesumi Kuwashima, Takio Kurita
A combination of Deep CNNs and Skip connection layers is used as a feature extractor for image features on both local and global area.
Ranked #20 on Image Super-Resolution on Set14 - 2x upscaling
no code implementations • 28 Mar 2017 • Shohei Kumagai, Kazuhiro Hotta, Takio Kurita
In this paper, we propose to predict the number of targets using multiple CNNs specialized to a specific appearance, and those CNNs are adaptively selected according to the appearance of a test image.
no code implementations • 8 Nov 2016 • Toru Tamaki, Shoji Sonoyama, Takio Kurita, Tsubasa Hirakawa, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Shigeto Yoshida, Hiroshi Mieno, Shinji Tanaka, Kazuaki Chayama
This paper proposes a method for domain adaptation that extends the maximum margin domain transfer (MMDT) proposed by Hoffman et al., by introducing L2 distance constraints between samples of different domains; thus, our method is denoted as MMDTL2.