Search Results for author: Hitoshi Iyatomi

Found 24 papers, 6 papers with code

Validity-Based Sampling and Smoothing Methods for Multiple Reference Image Captioning

no code implementations NAACL (maiworkshop) 2021 Shunta Nagasawa, Yotaro Watanabe, Hitoshi Iyatomi

In image captioning, multiple captions are often provided as ground truths, since a valid caption is not always uniquely determined.

Image Captioning

Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired

no code implementations17 Nov 2022 Kazuya Ohata, Shunsuke Kitada, Hitoshi Iyatomi

We propose a simple yet effective image captioning framework that can determine the quality of an image and notify the user of the reasons for any flaws in the image.

Image Captioning

Loc-VAE: Learning Structurally Localized Representation from 3D Brain MR Images for Content-Based Image Retrieval

no code implementations2 Oct 2022 Kei Nishimaki, Kumpei Ikuta, Yuto Onga, Hitoshi Iyatomi, Kenichi Oishi

Loc-VAE is based on $\beta$-VAE with the additional constraint that each dimension of the low-dimensional representation corresponds to a local region of the brain.

Content-Based Image Retrieval Dimensionality Reduction +1

DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention

no code implementations7 Sep 2022 Shunsuke Kitada, Yuki Iwazaki, Riku Togashi, Hitoshi Iyatomi

There is increasing interest in the use of multimodal data in various web applications, such as digital advertising and e-commerce.

Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents

no code implementations30 Aug 2022 Tsubasa Nakagawa, Shunsuke Kitada, Hitoshi Iyatomi

The proposed framework consists of a bidirectional encoder representations from transformers (BERT)-based detector that detects sentences causing differences in emotion recognition and an analysis that acquires expressions that characteristically appear in such sentences.

Emotion Recognition

Ad Creative Discontinuation Prediction with Multi-Modal Multi-Task Neural Survival Networks

no code implementations2 Apr 2022 Shunsuke Kitada, Hitoshi Iyatomi, Yoshifumi Seki

To improve the prediction performance for the two different types of discontinuations and for the ad creatives that contribute to sales, we introduce two new techniques: (1) a two-term estimation technique with multi-task learning and (2) a click-through rate-weighting technique for the loss function.

Multi-Task Learning Survival Analysis

Gastric Cancer Detection from X-ray Images Using Effective Data Augmentation and Hard Boundary Box Training

no code implementations18 Aug 2021 Hideaki Okamoto, Takakiyo Nomura, Kazuhito Nabeshima, Jun Hashimoto, Hitoshi Iyatomi

The proposed sfGAIA and HBBT significantly enhance the performance of the EfficientDet-D7 network by 5. 9% in terms of the F1-score, and our screening method reaches a practical screening capability for gastric cancer (F1: 57. 8%, recall: 90. 2%, precision: 42. 5%).

Image Augmentation

Disease-oriented image embedding with pseudo-scanner standardization for content-based image retrieval on 3D brain MRI

no code implementations14 Aug 2021 Hayato Arai, Yuto Onga, Kumpei Ikuta, Yusuke Chayama, Hitoshi Iyatomi, Kenichi Oishi

Compared with the baseline condition, our PSS reduced the variability in the distance from Alzheimer's disease (AD) to clinically normal (CN) and Parkinson disease (PD) cases by 15. 8-22. 6% and 18. 0-29. 9%, respectively.

Content-Based Image Retrieval Dimensionality Reduction +3

Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training

no code implementations18 Apr 2021 Shunsuke Kitada, Hitoshi Iyatomi

That is, even if the model using our VAT-based technique is trained on unlabeled data from a source other than the target task, both the prediction performance and model interpretability can be improved.

Semi-Supervised Text Classification text-classification

Bulk Production Augmentation Towards Explainable Melanoma Diagnosis

no code implementations3 Mar 2021 Kasumi Obi, Quan Huu Cap, Noriko Umegaki-Arao, Masaru Tanaka, Hitoshi Iyatomi

Although highly accurate automated diagnostic techniques for melanoma have been reported, the realization of a system capable of providing diagnostic evidence based on medical indices remains an open issue because of difficulties in obtaining reliable training data.

Data Augmentation

MIINet: An Image Quality Improvement Framework for Supporting Medical Diagnosis

no code implementations28 Nov 2020 Quan Huu Cap, Hitoshi Iyatomi, Atsushi Fukuda

Medical images have been indispensable and useful tools for supporting medical experts in making diagnostic decisions.

Image-to-Image Translation Medical Diagnosis +1

LASSR: Effective Super-Resolution Method for Plant Disease Diagnosis

no code implementations12 Oct 2020 Quan Huu Cap, Hiroki Tani, Hiroyuki Uga, Satoshi Kagiwada, Hitoshi Iyatomi

The collection of high-resolution training data is crucial in building robust plant disease diagnosis systems, since such data have a significant impact on diagnostic performance.

Super-Resolution

Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training

1 code implementation25 Sep 2020 Shunsuke Kitada, Hitoshi Iyatomi

To overcome the vulnerability to perturbations in the mechanism, we are inspired by adversarial training (AT), which is a powerful regularization technique for enhancing the robustness of the models.

AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss

1 code implementation ACL 2020 Mahmoud Daif, Shunsuke Kitada, Hitoshi Iyatomi

Classical and some deep learning techniques for Arabic text classification often depend on complex morphological analysis, word segmentation, and hand-crafted feature engineering.

Classification Document Classification +4

LeafGAN: An Effective Data Augmentation Method for Practical Plant Disease Diagnosis

1 code implementation24 Feb 2020 Quan Huu Cap, Hiroyuki Uga, Satoshi Kagiwada, Hitoshi Iyatomi

LeafGAN generates a wide variety of diseased images via transformation from healthy images, as a data augmentation tool for improving the performance of plant disease diagnosis.

Data Augmentation Image-to-Image Translation +1

Super-Resolution for Practical Automated Plant Disease Diagnosis System

no code implementations26 Nov 2019 Quan Huu Cap, Hiroki Tani, Hiroyuki Uga, Satoshi Kagiwada, Hitoshi Iyatomi

Automated plant diagnosis using images taken from a distance is often insufficient in resolution and degrades diagnostic accuracy since the important external characteristics of symptoms are lost.

Super-Resolution

AOP: An Anti-overfitting Pretreatment for Practical Image-based Plant Diagnosis

no code implementations25 Nov 2019 Takumi Saikawa, Quan Huu Cap, Satoshi Kagiwada, Hiroyuki Uga, Hitoshi Iyatomi

As a result, overfitting due to latent similarities in the dataset often occurs, and the diagnostic performance on real unseen data (e, g.

A comparable study: Intrinsic difficulties of practical plant diagnosis from wide-angle images

no code implementations25 Oct 2019 Katsumasa Suwa, Quan Huu Cap, Ryunosuke Kotani, Hiroyuki Uga, Satoshi Kagiwada, Hitoshi Iyatomi

Practical automated detection and diagnosis of plant disease from wide-angle images (i. e. in-field images containing multiple leaves using a fixed-position camera) is a very important application for large-scale farm management, in view of the need to ensure global food security.

Management Object Recognition

Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creative

1 code implementation17 May 2019 Shunsuke Kitada, Hitoshi Iyatomi, Yoshifumi Seki

Furthermore, conditional attention focuses attention of each ad creative with the consideration of its genre and target gender, thus improving conversion prediction accuracy.

Multi-Task Learning

End-to-End Text Classification via Image-based Embedding using Character-level Networks

1 code implementation8 Oct 2018 Shunsuke Kitada, Ryunosuke Kotani, Hitoshi Iyatomi

For analysing and/or understanding languages having no word boundaries based on morphological analysis such as Japanese, Chinese, and Thai, it is desirable to perform appropriate word segmentation before word embeddings.

Document Classification General Classification +3

Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning

no code implementations7 Sep 2018 Shunsuke Kitada, Hitoshi Iyatomi

In this report, we introduce the outline of our system in Task 3: Disease Classification of ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection.

Classification Data Augmentation +3

Lesion Border Detection in Dermoscopy Images Using Ensembles of Thresholding Methods

no code implementations26 Dec 2013 M. Emre Celebi, Quan Wen, Sae Hwang, Hitoshi Iyatomi, Gerald Schaefer

Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions.

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