Search Results for author: Masanari Kimura

Found 11 papers, 4 papers with code

SHIFT15M: Multiobjective Large-Scale Fashion Dataset with Distributional Shifts

2 code implementations30 Aug 2021 Masanari Kimura, Takuma Nakamura, Yuki Saito

In this paper, we propose SHIFT15M, a dataset that can be used to properly evaluate models in situations where the distribution of data changes between training and testing.

$α$-Geodesical Skew Divergence

1 code implementation31 Mar 2021 Masanari Kimura, Hideitsu Hino

The asymmetric skew divergence smooths one of the distributions by mixing it, to a degree determined by the parameter $\lambda$, with the other distribution.

Density Fixing: Simple yet Effective Regularization Method based on the Class Prior

1 code implementation8 Jul 2020 Masanari Kimura, Ryohei Izawa

Machine learning models suffer from overfitting, which is caused by a lack of labeled data.

Large-Scale Landslides Detection from Satellite Images with Incomplete Labels

no code implementations16 Oct 2019 Masanari Kimura

Earthquakes and tropical cyclones cause the suffering of millions of people around the world every year.

New Perspective of Interpretability of Deep Neural Networks

no code implementations12 Sep 2019 Masanari Kimura, Masayuki Tanaka

Improving the interpretability of DNNs is one of the hot research topics.

Intentional Attention Mask Transformation for Robust CNN Classification

no code implementations7 May 2019 Masanari Kimura, Masayuki Tanaka

To tackle this problem, we exploit a multi-channel attention mechanism in feature space.

General Classification

Interpretation of Feature Space using Multi-Channel Attentional Sub-Networks

no code implementations30 Apr 2019 Masanari Kimura, Masayuki Tanaka

To tackle this problem, we exploit a multi-channel attention mechanism in feature space.

Anomaly Detection Using GANs for Visual Inspection in Noisy Training Data

no code implementations3 Jul 2018 Masanari Kimura, Takashi Yanagihara

The proposed method detects pixel-level micro anomalies with a high accuracy from 1024x1024 high resolution images which are actually used in an industrial scene.

Unsupervised Anomaly Detection

Node Centralities and Classification Performance for Characterizing Node Embedding Algorithms

1 code implementation18 Feb 2018 Kento Nozawa, Masanari Kimura, Atsunori Kanemura

Embedding graph nodes into a vector space can allow the use of machine learning to e. g. predict node classes, but the study of node embedding algorithms is immature compared to the natural language processing field because of a diverse nature of graphs.

General Classification

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