1 citations · 3 across the 11 of their papers we have counts for
5 papers · 1 filter
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, enabling a wide range of applications,…
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 Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching
Shohei Enomoto, Naoya Hasegawa, Kazuki Adachi +4
Deep neural networks have achieved remarkable success in a variety of computer vision applications. However, there is a problem of degrading accuracy when the data distribution shi…
Test-time Similarity Modification for Person Re-identification toward Temporal Distribution Shift
Kazuki Adachi, Shohei Enomoto, Taku Sasaki +1
Person re-identification (re-id), which aims to retrieve images of the same person in a given image from a database, is one of the most practical image recognition applications. In…
Learning Robust Convolutional Neural Networks with Relevant Feature Focusing via Explanations
Kazuki Adachi, Shin'ya Yamaguchi
Existing image recognition techniques based on convolutional neural networks (CNNs) basically assume that the training and test datasets are sampled from i.i.d distributions. Howev…