1.5k citations · 2.1k across the 52 of their papers we have counts for
53 papers
WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks
Atsuyuki Miyai, Zaiying Zhao, Kazuki Egashira +9
Powered by large language models (LLMs), web browsing agents operate graphical user interfaces in a human-like manner, offering a transparent and general framework for automating w…
Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang +10
Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety of machine learning systems and has shaped the field of OOD detection. Meanwhile, several other probl…
Rethinking Momentum Knowledge Distillation in Online Continual Learning
Nicolas Michel, Maorong Wang, Ling Xiao +1
Online Continual Learning (OCL) addresses the problem of training neural networks on a continuous data stream where multiple classification tasks emerge in sequence. In contrast to…
New metrics for analyzing continual learners
Nicolas Michel, Giovanni Chierchia, Romain Negrel +2
Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, i…
BSED: Baseline Shapley-Based Explainable Detector
Michihiro Kuroki, Toshihiko Yamasaki
Explainable artificial intelligence (XAI) has witnessed significant advances in the field of object recognition, with saliency maps being used to highlight image features relevant…
Personalized Image Enhancement Featuring Masked Style Modeling
Satoshi Kosugi, Toshihiko Yamasaki
We address personalized image enhancement in this study, where we enhance input images for each user based on the user's preferred images. Previous methods apply the same preferred…
Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter
Satoshi Kosugi, Toshihiko Yamasaki
In this study, we address local photo enhancement to improve the aesthetic quality of an input image by applying different effects to different regions. Existing photo enhancement…
MetaMixer: A Regularization Strategy for Online Knowledge Distillation
Maorong Wang, Ling Xiao, Toshihiko Yamasaki
Online knowledge distillation (KD) has received increasing attention in recent years. However, while most existing online KD methods focus on developing complicated model structure…
Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer
Dichao Liu, Toshihiko Yamasaki, Yu Wang +2
The number of traffic accidents has been continuously increasing in recent years worldwide. Many accidents are caused by distracted drivers, who take their attention away from driv…
Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval
Ling Xiao, Toshihiko Yamasaki
Fine-grained fashion retrieval searches for items that share a similar attribute with the query image. Most existing methods use a pre-trained feature extractor (e.g., ResNet 50) t…
Semi-supervised Fashion Compatibility Prediction by Color Distortion Prediction
Ling Xiao, Toshihiko Yamasaki
Supervised learning methods have been suffering from the fact that a large-scale labeled dataset is mandatory, which is difficult to obtain. This has been a more significant issue…
Fine-Grained Image Style Transfer with Visual Transformers
Jianbo Wang, Huan Yang, Jianlong Fu +2
With the development of the convolutional neural network, image style transfer has drawn increasing attention. However, most existing approaches adopt a global feature transformati…
Improving Robustness to Out-of-Distribution Data by Frequency-based Augmentation
Koki Mukai, Soichiro Kumano, Toshihiko Yamasaki
Although Convolutional Neural Networks (CNNs) have high accuracy in image recognition, they are vulnerable to adversarial examples and out-of-distribution data, and the difference…
SAT: Self-adaptive training for fashion compatibility prediction
Ling Xiao, Toshihiko Yamasaki
This paper presents a self-adaptive training (SAT) model for fashion compatibility prediction. It focuses on the learning of some hard items, such as those that share similar color…
Superclass Adversarial Attack
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken. For example, when an automatic d…
Green Hierarchical Vision Transformer for Masked Image Modeling
Lang Huang, Shan You, Mingkai Zheng +3
We present an efficient approach for Masked Image Modeling (MIM) with hierarchical Vision Transformers (ViTs), allowing the hierarchical ViTs to discard masked patches and operate…
Detecting Deepfakes with Self-Blended Images
Kaede Shiohara, Toshihiko Yamasaki
In this paper, we present novel synthetic training data called self-blended images (SBIs) to detect deepfakes. SBIs are generated by blending pseudo source and target images from s…
Learning Where to Learn in Cross-View Self-Supervised Learning
Lang Huang, Shan You, Mingkai Zheng +3
Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection…
Subjective Functionality and Comfort Prediction for Apartment Floor Plans and Its Application to Intuitive Searches
Taro Narahara, Toshihiko Yamasaki
This study presents a new user experience in apartment searches using functionality and comfort as query items. This study has three technical contributions. First, we present a ne…
Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks
Tetsu Kasanishi, Xueting Wang, Toshihiko Yamasaki
Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property predic…
Location Prediction via Bi-direction Speculation and Dual-level Association
Xixi Li1, Ruimin Hu, Zheng Wang +1
Location prediction is of great importance in location-based applications for the construction of the smart city. To our knowledge, existing models for location prediction focus on…
Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering
Pengyu Xie, Xin Xu, Zheng Wang +1
Unsupervised video-based person re-identification (re-ID) methods extract richer features from video tracklets than image-based ones. The state-of-the-art methods utilize clusterin…
Learning from Synthetic Shadows for Shadow Detection and Removal
Naoto Inoue, Toshihiko Yamasaki
Shadow removal is an essential task in computer vision and computer graphics. Recent shadow removal approaches all train convolutional neural networks (CNN) on real paired shadow/s…
Predicting Online Video Advertising Effects with Multimodal Deep Learning
Jun Ikeda, Hiroyuki Seshime, Xueting Wang +1
With expansion of the video advertising market, research to predict the effects of video advertising is getting more attention. Although effect prediction of image advertising has…