20 citations · 48 across the 20 of their papers we have counts for
3 papers · 1 filter
Post-pre-training for Modality Alignment in Vision-Language Foundation Models
Shin'ya Yamaguchi, Dewei Feng, Sekitoshi Kanai +2
Contrastive language image pre-training (CLIP) is an essential component of building modern vision-language foundation models. While CLIP demonstrates remarkable zero-shot performa…
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…
F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain
Shin'ya Yamaguchi, Sekitoshi Kanai
Generative adversarial networks built from deep convolutional neural networks (GANs) lack the ability to exactly replicate the high-frequency components of natural images. To allev…