4 papers
CLIP-like Model as a Foundational Density Ratio Estimator
Fumiya Uchiyama, Rintaro Yanagi, Shohei Taniguchi +5
Density ratio estimation is a core concept in statistical machine learning because it provides a unified mechanism for tasks such as importance weighting, divergence estimation, an…
PowerCLIP: Powerset Alignment for Contrastive Pre-Training
Masaki Kawamura, Nakamasa Inoue, Rintaro Yanagi +2
Contrastive vision-language pre-training frameworks such as CLIP have demonstrated impressive zero-shot performance across a range of vision-language tasks. Recent studies have sho…
MoireMix: A Formula-Based Data Augmentation for Improving Image Classification Robustness
Yuto Matsuo, Yoshihiro Fukuhara, Yuki M. Asano +3
Data augmentation is a key technique for improving the robustness of image classification models. However, many recent approaches rely on diffusion-based synthesis or complex featu…
Approximate Domain Unlearning for Vision-Language Models
Kodai Kawamura, Yuta Goto, Rintaro Yanagi +2
Pre-trained Vision-Language Models (VLMs) exhibit strong generalization capabilities, enabling them to recognize a wide range of objects across diverse domains without additional t…