107 citations · 123 across the 13 of their papers we have counts for
13 papers
Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
Hiroki Naganuma, Taiji Suzuki, Rio Yokota +3
Generalization measures have been studied extensively in the machine learning community to better characterize generalization gaps. However, establishing a reliable generalization…
Fixed-Weight Difference Target Propagation
Tatsukichi Shibuya, Nakamasa Inoue, Rei Kawakami +1
Target Propagation (TP) is a biologically more plausible algorithm than the error backpropagation (BP) to train deep networks, and improving practicality of TP is an open issue. TP…
Informative Sample-Aware Proxy for Deep Metric Learning
Aoyu Li, Ikuro Sato, Kohta Ishikawa +2
Among various supervised deep metric learning methods proxy-based approaches have achieved high retrieval accuracies. Proxies, which are class-representative points in an embedding…
PoF: Post-Training of Feature Extractor for Improving Generalization
Ikuro Sato, Ryota Yamada, Masayuki Tanaka +2
It has been intensively investigated that the local shape, especially flatness, of the loss landscape near a minimum plays an important role for generalization of deep models. We d…
Feature Space Particle Inference for Neural Network Ensembles
Shingo Yashima, Teppei Suzuki, Kohta Ishikawa +2
Ensembles of deep neural networks demonstrate improved performance over single models. For enhancing the diversity of ensemble members while keeping their performance, particle-bas…
Implicit Neural Representations for Variable Length Human Motion Generation
Pablo Cervantes, Yusuke Sekikawa, Ikuro Sato +1
We propose an action-conditional human motion generation method using variational implicit neural representations (INR). The variational formalism enables action-conditional distri…
Adversarial Transformations for Semi-Supervised Learning
Teppei Suzuki, Ikuro Sato
We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning. RAT is designed to enhance robustness of the output distribution of c…
Breaking Inter-Layer Co-Adaptation by Classifier Anonymization
Ikuro Sato, Kohta Ishikawa, Guoqing Liu +1
This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier…
Generating Easy-to-Understand Referring Expressions for Target Identifications
Mikihiro Tanaka, Takayuki Itamochi, Kenichi Narioka +3
This paper addresses the generation of referring expressions that not only refer to objects correctly but also let humans find them quickly. As a target becomes relatively less sal…
Canonical and Compact Point Cloud Representation for Shape Classification
Kent Fujiwara, Ikuro Sato, Mitsuru Ambai +2
We present a novel compact point cloud representation that is inherently invariant to scale, coordinate change and point permutation. The key idea is to parametrize a distance fiel…
Binary-decomposed DCNN for accelerating computation and compressing model without retraining
Ryuji Kamiya, Takayoshi Yamashita, Mitsuru Ambai +3
Recent trends show recognition accuracy increasing even more profoundly. Inference process of Deep Convolutional Neural Networks (DCNN) has a large number of parameters, requires a…
APAC: Augmented PAttern Classification with Neural Networks
Ikuro Sato, Hiroki Nishimura, Kensuke Yokoi
Deep neural networks have been exhibiting splendid accuracies in many of visual pattern classification problems. Many of the state-of-the-art methods employ a technique known as da…
Pairwise Rotation Hashing for High-dimensional Features
Kohta Ishikawa, Ikuro Sato, Mitsuru Ambai
Binary Hashing is widely used for effective approximate nearest neighbors search. Even though various binary hashing methods have been proposed, very few methods are feasible for e…