4 citations · 7 across the 15 of their papers we have counts for
15 papers
SCoRe: Clean Image Generation from Diffusion Models Trained on Noisy Images
Yuta Matsuzaki, Seiichi Uchida, Shumpei Takezaki
Diffusion models trained on noisy datasets often reproduce high-frequency training artifacts, significantly degrading generation quality. To address this, we propose SCoRe (Spectra…
Learning from Partial Label Proportions for Whole Slide Image Segmentation
Shinnosuke Matsuo, Daiki Suehiro, Seiichi Uchida +4
In this paper, we address the segmentation of tumor subtypes in whole slide images (WSI) by utilizing incomplete label proportions. Specifically, we utilize `partial' label proport…
Bounding the Worst-class Error: A Boosting Approach
Yuya Saito, Shinnosuke Matsuo, Seiichi Uchida +1
This paper tackles the problem of the worst-class error rate, instead of the standard error rate averaged over all classes. For example, a three-class classification task with clas…
Deep Attentive Time Warping
Shinnosuke Matsuo, Xiaomeng Wu, Gantugs Atarsaikhan +4
Similarity measures for time series are important problems for time series classification. To handle the nonlinear time distortions, Dynamic Time Warping (DTW) has been widely used…
Functional Knowledge Transfer with Self-supervised Representation Learning
Prakash Chandra Chhipa, Muskaan Chopra, Gopal Mengi +7
This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer. In this work, functional knowledge tra…
Cluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification
Shota Harada, Ryoma Bise, Kengo Araki +7
Semi-supervised domain adaptation is a technique to build a classifier for a target domain by modifying a classifier in another (source) domain using many unlabeled samples and a s…
Disease Severity Regression with Continuous Data Augmentation
Shumpei Takezaki, Kiyohito Tanaka, Seiichi Uchida +1
Disease severity regression by a convolutional neural network (CNN) for medical images requires a sufficient number of image samples labeled with severity levels. Conditional gener…
Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization
Shinnosuke Matsuo, Ryoma Bise, Seiichi Uchida +1
This paper proposes a novel and efficient method for Learning from Label Proportions (LLP), whose goal is to train a classifier only by using the class label proportions of instanc…
Depth Contrast: Self-Supervised Pretraining on 3DPM Images for Mining Material Classification
Prakash Chandra Chhipa, Richa Upadhyay, Rajkumar Saini +4
This work presents a novel self-supervised representation learning method to learn efficient representations without labels on images from a 3DPM sensor (3-Dimensional Particle Mea…
Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data
Takeaki Kadota, Hideaki Hayashi, Ryoma Bise +2
Automatic image-based disease severity estimation generally uses discrete (i.e., quantized) severity labels. Annotating discrete labels is often difficult due to the images with am…
MontageGAN: Generation and Assembly of Multiple Components by GANs
Chean Fei Shee, Seiichi Uchida
A multi-layer image is more valuable than a single-layer image from a graphic designer's perspective. However, most of the proposed image generation methods so far focus on single-…
Revealing Reliable Signatures by Learning Top-Rank Pairs
Xiaotong Ji, Yan Zheng, Daiki Suehiro +1
Signature verification, as a crucial practical documentation analysis task, has been continuously studied by researchers in machine learning and pattern recognition fields. In spec…
Font Generation with Missing Impression Labels
Seiya Matsuda, Akisato Kimura, Seiichi Uchida
Our goal is to generate fonts with specific impressions, by training a generative adversarial network with a font dataset with impression labels. The main difficulty is that font i…
Magnification Prior: A Self-Supervised Method for Learning Representations on Breast Cancer Histopathological Images
Prakash Chandra Chhipa, Richa Upadhyay, Gustav Grund Pihlgren +3
This work presents a novel self-supervised pre-training method to learn efficient representations without labels on histopathology medical images utilizing magnification factors. O…
No Regret Sample Selection with Noisy Labels
H. Song, N. Mitsuo, S. Uchida +1
Deep neural networks (DNNs) suffer from noisy-labeled data because of the risk of overfitting. To avoid the risk, in this paper, we propose a novel DNN training method with sample…