3 papers
cs.LG2025
High-Performance Self-Supervised Learning by Joint Training of Flow Matching
Kosuke Ukita, Tsuyoshi Okita
Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality a…
cs.CV2025
Multimodal Foundation Model for Cross-Modal Retrieval and Activity Recognition Tasks
Koki Matsuishi, Kosuke Ukita, Tsuyoshi Okita
In recent years, the widespread adoption of wearable devices has highlighted the growing importance of behavior analysis using IMU. While applications span diverse fields such as h…
cs.LG2025
Image Classification Using a Diffusion Model as a Pre-Training Model
Kosuke Ukita, Ye Xiaolong, Tsuyoshi Okita
In this paper, we propose a diffusion model that integrates a representation-conditioning mechanism, where the representations derived from a Vision Transformer (ViT) are used to c…