Takahiro Ogawa
YOU?
Author Swipe
View article: Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustness
Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustness Open
We propose a novel continual self-supervised learning (CSSL) framework for simultaneously learning diverse features from multi-window-obtained chest computed tomography (CT) images and ensuring data privacy. Achieving a robust and highly g…
View article: Context-aware Image-to-Music Generation via Bridging Modalities through Musical Captions
Context-aware Image-to-Music Generation via Bridging Modalities through Musical Captions Open
View article: Deep-learning-based automatic liver segmentation using computed tomography images in dogs
Deep-learning-based automatic liver segmentation using computed tomography images in dogs Open
Introduction Deep learning-based automated segmentation has significantly improved the efficiency and accuracy of human medicine applications. However, veterinary applications, particularly canine liver segmentation, remain limited. This s…
View article: Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning
Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning Open
Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL). However, existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and inefficient knowledge sha…
View article: GeoJapan Fusion Framework: A Large Multimodal Model for Regional Remote Sensing Recognition
GeoJapan Fusion Framework: A Large Multimodal Model for Regional Remote Sensing Recognition Open
Recent advances in large multimodal models (LMMs) have opened new opportunities for multitask recognition from remote sensing images. However, existing approaches still face challenges in effectively recognizing the complex geospatial char…
View article: Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition
Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition Open
Visual Emotion Recognition (VER) is an important research topic due to its wide range of applications, including opinion mining and advertisement design. Extending this capability to recognize emotions at the individual level further broad…
View article: Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classification
Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classification Open
We propose a novel medical image classification method that integrates dual-model weight selection with self-knowledge distillation (SKD). In real-world medical settings, deploying large-scale models is often limited by computational resou…
View article: Information-Guided Diffusion Sampling for Dataset Distillation
Information-Guided Diffusion Sampling for Dataset Distillation Open
Dataset distillation aims to create a compact dataset that retains essential information while maintaining model performance. Diffusion models (DMs) have shown promise for this task but struggle in low images-per-class (IPC) settings, wher…
View article: Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling
Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling Open
To alleviate the reliance of deep neural networks on large-scale datasets, dataset distillation aims to generate compact, high-quality synthetic datasets that can achieve comparable performance to the original dataset. The integration of g…
View article: Hyperbolic Dataset Distillation
Hyperbolic Dataset Distillation Open
To address the computational and storage challenges posed by large-scale datasets in deep learning, dataset distillation has been proposed to synthesize a compact dataset that replaces the original while maintaining comparable model perfor…
View article: Diversity-Driven Generative Dataset Distillation Based on Diffusion Model with Self-Adaptive Memory
Diversity-Driven Generative Dataset Distillation Based on Diffusion Model with Self-Adaptive Memory Open
Dataset distillation enables the training of deep neural networks with comparable performance in significantly reduced time by compressing large datasets into small and representative ones. Although the introduction of generative models ha…
View article: Analysis of Model Merging Methods for Continual Updating of Foundation Models in Distributed Data Settings
Analysis of Model Merging Methods for Continual Updating of Foundation Models in Distributed Data Settings Open
Foundation models have achieved remarkable success across various domains, but still face critical challenges such as limited data availability, high computational requirements, and rapid knowledge obsolescence. To address these issues, we…
View article: Enhancing Adversarial Defense via Brain Activity Integration Without Adversarial Examples
Enhancing Adversarial Defense via Brain Activity Integration Without Adversarial Examples Open
Adversarial attacks on large-scale vision–language foundation models, such as the contrastive language–image pretraining (CLIP) model, can significantly degrade performance across various tasks by generating adversarial examples that are i…
View article: Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence Open
In few-shot action recognition (FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the high computational complexity of mainstream Transformer-based methods limits their application. Recent Mamba…
View article: Personalized Federated Learning for Egocentric Video Gaze Estimation with Comprehensive Parameter Frezzing
Personalized Federated Learning for Egocentric Video Gaze Estimation with Comprehensive Parameter Frezzing Open
Egocentric video gaze estimation requires models to capture individual gaze patterns while adapting to diverse user data. Our approach leverages a transformer-based architecture, integrating it into a PFL framework where only the most sign…
View article: StarMAP: Global Neighbor Embedding for Faithful Data Visualization
StarMAP: Global Neighbor Embedding for Faithful Data Visualization Open
Neighbor embedding is widely employed to visualize high-dimensional data; however, it frequently overlooks the global structure, e.g., intercluster similarities, thereby impeding accurate visualization. To address this problem, this paper …
View article: Answer to the Letter to the Editor from Hinpetch Daungsupawong Concerning "Development of New Surgical Training for Full Endoscopic Surgery Using 3D-Printed Models"
Answer to the Letter to the Editor from Hinpetch Daungsupawong Concerning "Development of New Surgical Training for Full Endoscopic Surgery Using 3D-Printed Models" Open
View article: Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation
Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation Open
Composed Image Retrieval (CIR) provides an effective way to manage and access large-scale visual data. Construction of the CIR model utilizes triplets that consist of a reference image, modification text describing desired changes, and a t…
View article: Expert Comment Generation Considering Sports Skill Level Using a Large Multimodal Model with Video and Spatial-Temporal Motion Features
Expert Comment Generation Considering Sports Skill Level Using a Large Multimodal Model with Video and Spatial-Temporal Motion Features Open
In sports training, personalized skill assessment and feedback are crucial for athletes to master complex movements and improve performance. However, existing research on skill transfer predominantly focuses on skill evaluation through vid…
View article: Continual Self-supervised Learning Considering Medical Domain Knowledge in Chest CT Images
Continual Self-supervised Learning Considering Medical Domain Knowledge in Chest CT Images Open
We propose a novel continual self-supervised learning method (CSSL) considering medical domain knowledge in chest CT images. Our approach addresses the challenge of sequential learning by effectively capturing the relationship between prev…
View article: Generative Dataset Distillation Based on Self-knowledge Distillation
Generative Dataset Distillation Based on Self-knowledge Distillation Open
Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel gene…
View article: [Paper] Few-shot Personalized Saliency Prediction Based on Interpersonal Gaze Patterns
[Paper] Few-shot Personalized Saliency Prediction Based on Interpersonal Gaze Patterns Open
View article: Exponential Dissimilarity-Dispersion Family for Domain-Specific Representation Learning
Exponential Dissimilarity-Dispersion Family for Domain-Specific Representation Learning Open
This paper presents a new domain-specific representation learning method, exponential dissimilarity-dispersion family (EDDF), a novel distribution family that includes a dissimilarity function and a global dispersion parameter. In generati…
View article: Cross-Domain Multi-Step Thinking: Zero-Shot Fine-Grained Traffic Sign Recognition in the Wild
Cross-Domain Multi-Step Thinking: Zero-Shot Fine-Grained Traffic Sign Recognition in the Wild Open
View article: Enhancing Generative Class Incremental Learning Performance With a Model Forgetting Approach
Enhancing Generative Class Incremental Learning Performance With a Model Forgetting Approach Open
This study presents a novel approach to Generative Class Incremental Learning (GCIL) by introducing the forgetting mechanism, aimed at dynamically managing class information for better adaptation to streaming data. GCIL is one of the hot t…
View article: Enhancing Classification Models With Sophisticated Counterfactual Images
Enhancing Classification Models With Sophisticated Counterfactual Images Open
In deep learning, training data, which are mainly from realistic scenarios, often carry certain biases. This causes deep learning models to learn incorrect relationships between features when using these training data. However, because the…
View article: Efficacy of Viltolarsen in Improving Motor Function in Patients with Duchenne Muscular Dystrophy
Efficacy of Viltolarsen in Improving Motor Function in Patients with Duchenne Muscular Dystrophy Open
View article: LLM is Knowledge Graph Reasoner: LLM's Intuition-aware Knowledge Graph Reasoning for Cold-start Sequential Recommendation
LLM is Knowledge Graph Reasoner: LLM's Intuition-aware Knowledge Graph Reasoning for Cold-start Sequential Recommendation Open
Knowledge Graphs (KGs) represent relationships between entities in a graph structure and have been widely studied as promising tools for realizing recommendations that consider the accurate content information of items. However, traditiona…
View article: Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence Open
In few-shot action recognition (FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the high computational complexity of mainstream Transformer-based methods limits their application. Recent Mamba…
View article: Generalizing Human Motion Style Transfer Method Based on Metadata-independent Learning
Generalizing Human Motion Style Transfer Method Based on Metadata-independent Learning Open