45 citations · 164 across the 26 of their papers we have counts for
27 papers
Topology-Aware Parameter-Efficient Adaptation for Cross-Dataset Retinal Vessel Segmentation
Yongsong Huang, Tomo Miyazaki, Kai Xu +3
Retinal vessel segmentation in multi-domain deployment requires a source model to adapt to domains that differ in imaging conditions and annotation conventions. Conventional parame…
OGG-FR: Orthogonal Gradient Gaming and Frequency Rectification for Unmanned Aerial Vehicle Infrared Image Super-Resolution
Yongsong Huang, Qingzhong Wang, Xiaofeng Liu +3
Unmanned aerial vehicle (UAV) infrared image super-resolution aims to recover weak thermal structures for deployment on resource-constrained platforms; lightweight models are there…
Right Answer, Wrong Heat: Explanation-Aware Evaluation and Thermal-Grounded Feedback for MLLMs on Infrared Images
Yongsong Huang, Xiaofeng Liu, Tomo Miyazaki +2
General-purpose multimodal large language models (MLLMs) are increasingly applied to infrared images, where they are commonly scored by answer accuracy alone. However, a correct an…
Improving Adversarial Robustness via Activation Amplification and Attenuation
Taïga Gonçalves, Yongsong Huang, Tomo Miyazaki +1
The existence of adversarial attacks is often attributed to the presence of non-robust features in neural networks. While prior defenses reduce their impact via pruning, masking, o…
POCA: Pareto-Optimal Curriculum Alignment for Visual Text Generation
Yaohou Fan, Qingzhong Wang, Yongsong Huang +3
Current visual text generation models struggle with the trade-off between text accuracy and overall image coherence. We find that achieving high text accuracy can reduce aesthetic…
GTFMN: Guided Texture and Feature Modulation Network for Low-Light Image Enhancement and Super-Resolution
Yongsong Huang, Tzu-Hsuan Peng, Tomo Miyazaki +4
Low-light image super-resolution (LLSR) is a challenging task due to the coupled degradation of low resolution and poor illumination. To address this, we propose the Guided Texture…
U-Harmony: Enhancing Joint Training for Segmentation Models with Universal Harmonization
Weiwei Ma, Xiaobing Yu, Peijie Qiu +7
In clinical practice, medical segmentation datasets are often limited and heterogeneous, with variations in modalities, protocols, and anatomical targets across institutions. Exist…
Class-agnostic 3D Segmentation by Granularity-Consistent Automatic 2D Mask Tracking
Juan Wang, Yasutomo Kawanishi, Tomo Miyazaki +2
3D instance segmentation is an important task for real-world applications. To avoid costly manual annotations, existing methods have explored generating pseudo labels by transferri…
GPSMamba: A Global Phase and Spectral Prompt-guided Mamba for Infrared Image Super-Resolution
Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu +1
Infrared Image Super-Resolution (IRSR) is challenged by the low contrast and sparse textures of infrared data, requiring robust long-range modeling to maintain global coherence. Wh…
Joint Low-level and High-level Textual Representation Learning with Multiple Masking Strategies
Zhengmi Tang, Yuto Mitsui, Tomo Miyazaki +1
Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfull…
Towards Cross-Domain Multi-Targeted Adversarial Attacks
Taïga Gonçalves, Tomo Miyazaki, Shinichiro Omachi
Multi-targeted adversarial attacks aim to mislead classifiers toward specific target classes using a single perturbation generator with a conditional input specifying the desired t…
Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Model
Shoma Iwai, Atsuki Osanai, Shunsuke Kitada +1
Layout generation is a task to synthesize a harmonious layout with elements characterized by attributes such as category, position, and size. Human designers experiment with the pl…
DiCTI: Diffusion-based Clothing Designer via Text-guided Input
Ajda Lampe, Julija Stopar, Deepak Kumar Jain +3
Recent developments in deep generative models have opened up a wide range of opportunities for image synthesis, leading to significant changes in various creative fields, including…
Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model
Shoma Iwai, Tomo Miyazaki, Shinichiro Omachi
In recent years, neural network-driven image compression (NIC) has gained significant attention. Some works adopt deep generative models such as GANs and diffusion models to enhanc…
IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model
Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu +1
Infrared image super-resolution demands long-range dependency modeling and multi-scale feature extraction to address challenges such as homogeneous backgrounds, weak edges, and spa…
Learn From Orientation Prior for Radiograph Super-Resolution: Orientation Operator Transformer
Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu +3
Background and objective: High-resolution radiographic images play a pivotal role in the early diagnosis and treatment of skeletal muscle-related diseases. It is promising to enhan…
Infrared Image Super-Resolution via GAN
Yongsong Huang, Shinichiro Omachi
The ability of generative models to accurately fit data distributions has resulted in their widespread adoption and success in fields such as computer vision and natural language p…
Texture and Noise Dual Adaptation for Infrared Image Super-Resolution
Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu +2
Recent efforts have explored leveraging visible light images to enrich texture details in infrared (IR) super-resolution. However, this direct adaptation approach often becomes a d…
Deep Image Compression Using Scene Text Quality Assessment
Shohei Uchigasaki, Tomo Miyazaki, Shinichiro Omachi
Image compression is a fundamental technology for Internet communication engineering. However, a high compression rate with general methods may degrade images, resulting in unreada…
Infrared Image Super-Resolution: Systematic Review, and Future Trends
Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu +1
Image Super-Resolution (SR) is essential for a wide range of computer vision and image processing tasks. Investigating infrared (IR) image (or thermal images) super-resolution is a…
A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data
Zhengmi Tang, Tomo Miyazaki, Shinichiro Omachi
Scene-text image synthesis techniques that aim to naturally compose text instances on background scene images are very appealing for training deep neural networks due to their abil…
Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN
Yongsong Huang, Qingzhong Wang, Shinichiro Omachi
In this paper, we present a medical AttentIon Denoising Super Resolution Generative Adversarial Network (AID-SRGAN) for diographic image super-resolution. First, we present a medic…
Stroke-Based Scene Text Erasing Using Synthetic Data for Training
Zhengmi Tang, Tomo Miyazaki, Yoshihiro Sugaya +1
Scene text erasing, which replaces text regions with reasonable content in natural images, has drawn significant attention in the computer vision community in recent years. There a…
Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks
Shoma Iwai, Tomo Miyazaki, Yoshihiro Sugaya +1
We propose a GAN-based image compression method working at extremely low bitrates below 0.1bpp. Most existing learned image compression methods suffer from blur at extremely low bi…