7 citations · 7 across the 5 of their papers we have counts for
7 papers
A Riemannian Geometry for Low-rank Adaptation
Shoichiro Takeda, Shin'ya Yamaguchi, Satoshi Suzuki +1
Low-rank adaptation (LoRA) is widely used as a parameter-efficient fine-tuning technique for pre-trained deep neural networks, which approximates the weight update via full fine-tu…
LagrangeGS: Non-Conservative Lagrangian System on Dynamic 3D Gaussian Splatting
Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda +4
Dynamic 3D Gaussian Splatting (3DGS) achieves photorealistic reconstruction of time-varying scenes, and recent physics-aware extensions improve extrapolation by explicitly predicti…
Difference Vector Equalization for Robust Fine-tuning of Vision-Language Models
Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda +7
Contrastive pre-trained vision-language models, such as CLIP, demonstrate strong generalization abilities in zero-shot classification by leveraging embeddings extracted from image…
IPCD: Intrinsic Point-Cloud Decomposition
Shogo Sato, Takuhiro Kaneko, Shoichiro Takeda +5
Point clouds are widely used in various fields, including augmented reality (AR) and robotics, where relighting and texture editing are crucial for realistic visualization. Achievi…
Optimal Transport with Cyclic Symmetry
Shoichiro Takeda, Yasunori Akagi, Naoki Marumo +1
We propose novel fast algorithms for optimal transport (OT) utilizing a cyclic symmetry structure of input data. Such OT with cyclic symmetry appears universally in various real-wo…
Adversarial Finetuning with Latent Representation Constraint to Mitigate Accuracy-Robustness Tradeoff
Satoshi Suzuki, Shin'ya Yamaguchi, Shoichiro Takeda +4
This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial train…
Image Enhanced Rotation Prediction for Self-Supervised Learning
Shin'ya Yamaguchi, Sekitoshi Kanai, Tetsuya Shioda +1
The rotation prediction (Rotation) is a simple pretext-task for self-supervised learning (SSL), where models learn useful representations for target vision tasks by solving pretext…