60 citations · 144 across the 31 of their papers we have counts for
33 papers
Medical-Checklist: Assessing the Comprehension of Medical Images by Multimodal Models
Bannapol Limanond, Masanori Suganuma, Takayuki Okatani
This paper introduces a new benchmark test, Medical-Checklist, for assessing medical multimodal models. The recent advancements in multimodal models have demonstrated significant p…
Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method
Yan Zeng, Masanori Suganuma, Takayuki Okatani
This paper studies the problem of inverting the DDIM image generation process to recover latent variables, particularly the initial noise map, from a generated image. Existing meth…
MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval
Naoya Sogi, Takashi Shibata, Makoto Terao +2
Result diversification (RD) is a crucial technique in Text-to-Image Retrieval for enhancing the efficiency of a practical application. Conventional methods focus solely on increasi…
TB-Bench: Training and Testing Multi-Modal AI for Understanding Spatio-Temporal Traffic Behaviors from Dashcam Images/Videos
Korawat Charoenpitaks, Van-Quang Nguyen, Masanori Suganuma +4
The application of Multi-modal Large Language Models (MLLMs) in Autonomous Driving (AD) faces significant challenges due to their limited training on traffic-specific data and the…
RP-SLAM: Real-time Photorealistic SLAM with Efficient 3D Gaussian Splatting
Lizhi Bai, Chunqi Tian, Jun Yang +3
3D Gaussian Splatting has emerged as a promising technique for high-quality 3D rendering, leading to increasing interest in integrating 3DGS into realism SLAM systems. However, exi…
Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?
Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
Detecting objects occupying only small areas in an image is difficult, even for humans. Therefore, annotating small-size object instances is hard and thus costly. This study questi…
Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images
Xiangyong Lu, Masanori Suganuma, Takayuki Okatani
In real-world applications of image recognition tasks, such as human pose estimation, cameras often capture objects, like human bodies, at low resolutions. This scenario poses a ch…
Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability
Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
Open-vocabulary object detection (OVD), detecting specific classes of objects using only their linguistic descriptions (e.g., class names) without any image samples, has garnered s…
An Improved Method for Personalizing Diffusion Models
Yan Zeng, Masanori Suganuma, Takayuki Okatani
Diffusion models have demonstrated impressive image generation capabilities. Personalized approaches, such as textual inversion and Dreambooth, enhance model individualization usin…
SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers
Xiangyong Lu, Masanori Suganuma, Takayuki Okatani
Computer vision has become increasingly prevalent in solving real-world problems across diverse domains, including smart agriculture, fishery, and livestock management. These appli…
Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction
Korawat Charoenpitaks, Van-Quang Nguyen, Masanori Suganuma +3
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 accidents using a single…
That's BAD: Blind Anomaly Detection by Implicit Local Feature Clustering
Jie Zhang, Masanori Suganuma, Takayuki Okatani
Recent studies on visual anomaly detection (AD) of industrial objects/textures have achieved quite good performance. They consider an unsupervised setting, specifically the one-cla…
Contextual Affinity Distillation for Image Anomaly Detection
Jie Zhang, Masanori Suganuma, Takayuki Okatani
Previous works on unsupervised industrial anomaly detection mainly focus on local structural anomalies such as cracks and color contamination. While achieving significantly high de…
Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Image
Han Zou, Masanori Suganuma, Takayuki Okatani
Despite the recent advancement in the study of removing motion blur in an image, it is still hard to deal with strong blurs. While there are limits in removing blurs from a single…
RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution
Han Zou, Masanori Suganuma, Takayuki Okatani
Smartphones with multi-camera systems, featuring cameras with varying field-of-views (FoVs), are increasingly common. This variation in FoVs results in content differences across v…
GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features
Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani
Current state-of-the-art methods for image captioning employ region-based features, as they provide object-level information that is essential to describe the content of images; th…
Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation
Qian Ye, Masanori Suganuma, Takayuki Okatani
In this paper, we consider the problem in defocus image deblurring. Previous classical methods follow two-steps approaches, i.e., first defocus map estimation and then the non-blin…
Learning Regularized Multi-Scale Feature Flow for High Dynamic Range Imaging
Qian Ye, Masanori Suganuma, Jun Xiao +1
Reconstructing ghosting-free high dynamic range (HDR) images of dynamic scenes from a set of multi-exposure images is a challenging task, especially with large object motion and oc…
Rethinking Open-Set Object Detection: Issues, a New Formulation, and Taxonomy
Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
Open-set object detection (OSOD), a task involving the detection of unknown objects while accurately detecting known objects, has recently gained attention. However, we identify a…
Rethinking Unsupervised Domain Adaptation for Semantic Segmentation
Zhijie Wang, Masanori Suganuma, Takayuki Okatani
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 its high annotation co…
Symmetry-aware Neural Architecture for Embodied Visual Navigation
Shuang Liu, Takayuki Okatani
Visual exploration is a task that seeks to visit all the navigable areas of an environment as quickly as possible. The existing methods employ deep reinforcement learning (RL) as t…
Improved Few-shot Segmentation by Redefinition of the Roles of Multi-level CNN Features
Zhijie Wang, Masanori Suganuma, Takayuki Okatani
This study is concerned with few-shot segmentation, i.e., segmenting the region of an unseen object class in a query image, given support image(s) of its instances. The current met…
Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes
Wenzheng Song, Masanori Suganuma, Xing Liu +3
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 brightness of scenes…
Cross-Region Domain Adaptation for Class-level Alignment
Zhijie Wang, Xing Liu, Masanori Suganuma +1
Semantic segmentation requires a lot of training data, which necessitates costly annotation. There have been many studies on unsupervised domain adaptation (UDA) from one domain to…