47 citations · 164 across the 53 of their papers we have counts for
16 papers · 1 filter
Decoupled Audio-Visual Dataset Distillation
Wenyuan Li, Guang Li, Keisuke Maeda +2
Audio-Visual Dataset Distillation aims to compress large-scale datasets into compact subsets while preserving the performance of the original data. However, conventional Distributi…
Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV
Wenbo Huang, Jinghui Zhang, Zhenghao Chen +6
Wide-angle videos in few-shot action recognition (FSAR) effectively express actions within specific scenarios. However, without a global understanding of both subjects and backgrou…
Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustness
Ren Tasai, Guang Li, Ren Togo +9
We propose a novel continual self-supervised learning (CSSL) framework for simultaneously learning diverse features from multi-window-obtained chest computed tomography (CT) images…
Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning
Minghao Yang, Ren Togo, Guang Li +2
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 suf…
Objectness Similarity: Capturing Object-Level Fidelity in 3D Scene Evaluation
Yuiko Uchida, Ren Togo, Keisuke Maeda +2
This paper presents Objectness SIMilarity (OSIM), a novel evaluation metric for 3D scenes that explicitly focuses on "objects," which are fundamental units of human visual percepti…
Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition
Ryo Takahashi, Naoki Saito, Keisuke Maeda +2
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…
Dual-Model Weight Selection and Self-Knowledge Distillation for Medical Image Classification
Ayaka Tsutsumi, Guang Li, Ren Togo +3
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…
Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling
Mingzhuo Li, Guang Li, Jiafeng Mao +3
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 comparabl…
Information-Guided Diffusion Sampling for Dataset Distillation
Linfeng Ye, Shayan Mohajer Hamidi, Guang Li +3
Dataset distillation aims to create a compact dataset that retains essential information while maintaining model performance. Diffusion models (DMs) have shown promise for this tas…
Diversity-Driven Generative Dataset Distillation Based on Diffusion Model with Self-Adaptive Memory
Mingzhuo Li, Guang Li, Jiafeng Mao +2
Dataset distillation enables the training of deep neural networks with comparable performance in significantly reduced time by compressing large datasets into small and representat…
Hyperbolic Dataset Distillation
Wenyuan Li, Guang Li, Keisuke Maeda +2
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 repl…
Personalized Federated Learning for Egocentric Video Gaze Estimation with Comprehensive Parameter Frezzing
Yuhu Feng, Keisuke Maeda, Takahiro Ogawa +1
Egocentric video gaze estimation requires models to capture individual gaze patterns while adapting to diverse user data. Our approach leverages a transformer-based architecture, i…
StarMAP: Global Neighbor Embedding for Faithful Data Visualization
Koshi Watanabe, Keisuke Maeda, Takahiro Ogawa +1
Neighbor embedding is widely employed to visualize high-dimensional data; however, it frequently overlooks the global structure, e.g., intercluster similarities, thereby impeding a…
Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation
Kenta Uesugi, Naoki Saito, Keisuke Maeda +2
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 i…
Continual Self-supervised Learning Considering Medical Domain Knowledge in Chest CT Images
Ren Tasai, Guang Li, Ren Togo +7
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 lear…
Generative Dataset Distillation Based on Self-knowledge Distillation
Longzhen Li, Guang Li, Ren Togo +3
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…