Search Results for author: Ikuro Sato

Found 15 papers, 6 papers with code

GUMBEL-NERF: Representing Unseen Objects as Part-Compositional Neural Radiance Fields

no code implementations27 Oct 2024 Yusuke Sekikawa, Chingwei Hsu, Satoshi Ikehata, Rei Kawakami, Ikuro Sato

We propose Gumbel-NeRF, a mixture-of-expert (MoE) neural radiance fields (NeRF) model with a hindsight expert selection mechanism for synthesizing novel views of unseen objects.

Novel View Synthesis

Fixed-Weight Difference Target Propagation

1 code implementation19 Dec 2022 Tatsukichi Shibuya, Nakamasa Inoue, Rei Kawakami, Ikuro Sato

Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work?

Informative Sample-Aware Proxy for Deep Metric Learning

no code implementations18 Nov 2022 Aoyu Li, Ikuro Sato, Kohta Ishikawa, Rei Kawakami, Rio Yokota

Among various supervised deep metric learning methods proxy-based approaches have achieved high retrieval accuracies.

Metric Learning Retrieval

PoF: Post-Training of Feature Extractor for Improving Generalization

1 code implementation5 Jul 2022 Ikuro Sato, Ryota Yamada, Masayuki Tanaka, Nakamasa Inoue, Rei Kawakami

We developed a training algorithm called PoF: Post-Training of Feature Extractor that updates the feature extractor part of an already-trained deep model to search a flatter minimum.

Feature Space Particle Inference for Neural Network Ensembles

1 code implementation2 Jun 2022 Shingo Yashima, Teppei Suzuki, Kohta Ishikawa, Ikuro Sato, Rei Kawakami

Ensembles of deep neural networks demonstrate improved performance over single models.

Diversity

Implicit Neural Representations for Variable Length Human Motion Generation

1 code implementation25 Mar 2022 Pablo Cervantes, Yusuke Sekikawa, Ikuro Sato, Koichi Shinoda

We confirm that our method with a Transformer decoder outperforms all relevant methods on HumanAct12, NTU-RGBD, and UESTC datasets in terms of realism and diversity of generated motions.

Decoder Diversity +1

Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime

no code implementations29 Sep 2021 Hiroki Naganuma, Taiji Suzuki, Rio Yokota, Masahiro Nomura, Kohta Ishikawa, Ikuro Sato

Generalization measures are intensively studied in the machine learning community for better modeling generalization gaps.

Hyperparameter Optimization

Adversarial Transformations for Semi-Supervised Learning

no code implementations13 Nov 2019 Teppei Suzuki, Ikuro Sato

We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning.

General Classification Semi-Supervised Image Classification

Breaking Inter-Layer Co-Adaptation by Classifier Anonymization

no code implementations4 Jun 2019 Ikuro Sato, Kohta Ishikawa, Guoqing Liu, Masayuki Tanaka

This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network.

Canonical and Compact Point Cloud Representation for Shape Classification

no code implementations13 Sep 2018 Kent Fujiwara, Ikuro Sato, Mitsuru Ambai, Yuichi Yoshida, Yoshiaki Sakakura

We present a novel compact point cloud representation that is inherently invariant to scale, coordinate change and point permutation.

Classification General Classification

Binary-decomposed DCNN for accelerating computation and compressing model without retraining

no code implementations14 Sep 2017 Ryuji Kamiya, Takayoshi Yamashita, Mitsuru Ambai, Ikuro Sato, Yuji Yamauchi, Hironobu Fujiyoshi

Our method replaces real-valued inner-product computations with binary inner-product computations in existing network models to accelerate computation of inference and decrease model size without the need for retraining.

APAC: Augmented PAttern Classification with Neural Networks

no code implementations13 May 2015 Ikuro Sato, Hiroki Nishimura, Kensuke Yokoi

Our method is named as APAC: the Augmented PAttern Classification, which is a way of classification using the optimal decision rule for augmented data learning.

Classification Data Augmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.