4 papers
Uniformity First: Uniformity-aware Test-time Adaptation of Vision-language Models against Image Corruption
Kazuki Adachi, Shin'ya Yamaguchi, Tomoki Hamagami
Pre-trained vision-language models such as contrastive language-image pre-training (CLIP) have demonstrated a remarkable generalizability, which has enabled a wide range of applica…
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…
Test-time Adaptation for Regression by Subspace Alignment
Kazuki Adachi, Shin'ya Yamaguchi, Atsutoshi Kumagai +1
This paper investigates test-time adaptation (TTA) for regression, where a regression model pre-trained in a source domain is adapted to an unknown target distribution with unlabel…
Evaluating Time-Series Training Dataset through Lens of Spectrum in Deep State Space Models
Sekitoshi Kanai, Yasutoshi Ida, Kazuki Adachi +3
This study investigates a method to evaluate time-series datasets in terms of the performance of deep neural networks (DNNs) with state space models (deep SSMs) trained on the data…