Search Results - "Suganuma, Masanori"

Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration by Liu, Xing, Suganuma, Masanori, Sun, Zhun, Okatani, Takayuki

“…In this paper, we study design of deep neural networks for tasks of image restoration. We propose a novel style of residual connections dubbed "dual residual…”
Get full text

k‐Means Clustering for Prediction of Tensile Properties in Carbon Fiber‐Reinforced Polymer Composites by Kurita, Hiroki, Suganuma, Masanori, Wang, Yinli, Narita, Fumio

“…The application of computer algorithms to identify patterns in data is referred to as machine learning. The algorithms are used to learn complex relationships…”
Get full text

Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions by Suganuma, Masanori, Liu, Xing, Okatani, Takayuki

“…Many studies have been conducted so far on image restoration, the problem of restoring a clean image from its distorted version. There are many different types…”
Get full text

Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors by Hosoya, Yusuke, Suganuma, Masanori, Okatani, Takayuki

“…The employment of convolutional neural networks has led to significant performance improvement on the task of object detection. However, when applying existing…”
Get full text

Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes by Song, Wenzheng, Suganuma, Masanori, Liu, Xing, Shimobayashi, Noriyuki, Maruta, Daisuke, Okatani, Takayuki

“…This paper considers matching images of low-light scenes, aiming to widen the frontier of SfM and visual SLAM applications. Recent image sensors can record the…”
Get full text

Controlling an Autonomous Agent for Exploring Unknown Environments Using Switching Prelearned Modules by HATA, TAKAHITO, SUGANUMA, MASANORI, NAGAO, TOMOHARU

“…SUMMARY In this paper, we try to acquire various behavior patterns of autonomous exploration agent using several learning environments. In case of previous…”
Get full text

Rethinking unsupervised domain adaptation for semantic segmentation by Wang, Zhijie, Suganuma, Masanori, Okatani, Takayuki

“…Unsupervised domain adaptation (UDA) adapts a model trained on one domain (called source) to a novel domain (called target) using only unlabeled data. Due to…”
Get full text

Symmetry-aware Neural Architecture for Embodied Visual Navigation by Liu, Shuang, Suganuma, Masanori, Okatani, Takayuki

“…The existing methods for addressing visual navigation employ deep reinforcement learning as the standard tool for the task. However, they tend to be vulnerable…”
Get full text

Improved high dynamic range imaging using multi-scale feature flows balanced between task-orientedness and accuracy by Ye, Qian, Suganuma, Masanori, Okatani, Takayuki

“…Deep learning has made it possible to accurately generate high dynamic range (HDR) images from multiple images taken at different exposure settings, largely…”
Get full text

Evolution of Deep Convolutional Neural Networks Using Cartesian Genetic Programming by Suganuma, Masanori, Kobayashi, Masayuki, Shirakawa, Shinichi, Nagao, Tomoharu

“…The convolutional neural network (CNN), one of the deep learning models, has demonstrated outstanding performance in a variety of computer vision tasks…”
Get more information

That’s BAD: blind anomaly detection by implicit local feature clustering by Zhang, Jie, Suganuma, Masanori, Okatani, Takayuki

“…Recent studies on visual anomaly detection (AD) of industrial objects/textures have achieved quite good performance. They consider an unsupervised setting,…”
Get full text

Unsupervised domain adaptation for semantic segmentation via cross-region alignment by Wang, Zhijie, Liu, Xing, Suganuma, Masanori, Okatani, Takayuki

“…Semantic segmentation requires a lot of training data, which necessitates costly annotation. There have been many studies on unsupervised domain adaptation…”
Get full text

Contextual Affinity Distillation for Image Anomaly Detection by Zhang, Jie, Suganuma, Masanori, Okatani, Takayuki

“…Previous studies on unsupervised industrial anomaly detection mainly focus on 'structural' types of anomalies such as cracks and color contamination by…”
Get full text

Accurate Single-Image Defocus Deblurring Based on Improved Integration with Defocus Map Estimation by Ye, Qian, Suganuma, Masanori, Okatani, Takayuki

“…This paper considers the problem of single-image defocus deblurring, which involves removing blur in an input image caused by defocusing. Previous studies have…”
Get full text

Removal of Image Obstacles for Vehicle-mounted Surrounding Monitoring Cameras by Real-time Video Inpainting by Hirohashi, Yoshihiro, Narioka, Kenichi, Suganuma, Masanori, Liu, Xing, Tamatsu, Yukimasa, Okatani, Takayuki

“…One of the practical problems with surrounding view cameras (SMCs) of a vehicle is the degradation of image quality due to obstacles by substances adherent to…”
Get full text

SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers by Lu, Xiangyong, Suganuma, Masanori, Okatani, Takayuki

“…Computer vision has become increasingly prevalent in solving real-world problems across diverse domains, including smart agriculture, fishery, and livestock…”
Get full text

Network Pruning and Fine-tuning for Few-shot Industrial Image Anomaly Detection by Zhang, Jie, Suganuma, Masanori, Okatani, Takayuki

“…This paper focuses on industrial image anomaly detection and localization under few-shot settings. Since acquiring sufficient anomalous data is difficult,…”
Get full text

Hierarchical feature construction for image classification using Genetic Programming by Suganuma, Masanori, Tsuchiya, Daiki, Shirakawa, Shinichi, Nagao, Tomoharu

“…In this paper, we design a hierarchical feature construction method for image classification. Our method has two feature construction stages: (1) feature…”
Get full text

Improving visual question answering for bridge inspection by pre‐training with external data of image–text pairs by Kunlamai, Thannarot, Yamane, Tatsuro, Suganuma, Masanori, Chun, Pang‐Jo, Okatani, Takayaki

“…This paper explores the application of visual question answering (VQA) in bridge inspection using recent advancements in multimodal artificial intelligence…”
Get full text

Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction by Charoenpitaks, Korawat, Nguyen, Van-Quang, Suganuma, Masanori, Takahashi, Masahiro, Niihara, Ryoma, Okatani, Takayuki

“…This paper addresses the problem of predicting hazards that drivers may encounter while driving a car. We formulate it as a task of anticipating impending…”
Get full text