27 citations · 59 across the 12 of their papers we have counts for
12 papers · 1 filter
What-Where Transformer: A Slot-Centric Visual Backbone for Concurrent Representation and Localization
Ryota Yoshihashi, Masahiro Kada, Satoshi Ikehata +2
Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, a…
Teacher-Guided Routing for Sparse Vision Mixture-of-Experts
Masahiro Kada, Ryota Yoshihashi, Satoshi Ikehata +2
Recent progress in deep learning has been driven by increasingly large-scale models, but the resulting computational cost has become a critical bottleneck. Sparse Mixture of Expert…
VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction
Jiahao Zhang, Ryota Yoshihashi, Shunsuke Kitada +2
Large language models (LLMs) have proven effective for layout generation due to their ability to produce structure-description languages, such as HTML or JSON. In this paper, we ar…
Constant Rate Scheduling: A General Framework for Optimizing Diffusion Noise Schedule via Distributional Change
Shuntaro Okada, Kenji Doi, Ryota Yoshihashi +2
We propose a general framework for optimizing noise schedules in diffusion models, applicable to both training and sampling. Our method enforces a constant rate of change in the pr…
Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation
Ryota Yoshihashi, Yuya Otsuka, Kenji Doi +2
The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images. In semantic segmentation, one promising appro…
Ladder Siamese Network: a Method and Insights for Multi-level Self-Supervised Learning
Ryota Yoshihashi, Shuhei Nishimura, Dai Yonebayashi +3
Siamese-network-based self-supervised learning (SSL) suffers from slow convergence and instability in training. To alleviate this, we propose a framework to exploit intermediate se…
Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition
Ryota Yoshihashi, Tomohiro Tanaka, Kenji Doi +2
In the deployment of scene-text spotting systems on mobile platforms, lightweight models with low computation are preferable. In concept, end-to-end (E2E) text spotting is suitable…
Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approach
Ryota Yoshihashi, Rei Kawakami, Shaodi You +3
Detecting tiny objects in a high-resolution video is challenging because the visual information is little and unreliable. Specifically, the challenge includes very low resolution o…
Hybrid Loss for Learning Single-Image-based HDR Reconstruction
Kenta Moriwaki, Ryota Yoshihashi, Rei Kawakami +2
This paper tackles high-dynamic-range (HDR) image reconstruction given only a single low-dynamic-range (LDR) image as input. While the existing methods focus on minimizing the mean…
Classification-Reconstruction Learning for Open-Set Recognition
Ryota Yoshihashi, Wen Shao, Rei Kawakami +3
Open-set classification is a problem of handling `unknown' classes that are not contained in the training dataset, whereas traditional classifiers assume that only known classes ap…
Cross-connected Networks for Multi-task Learning of Detection and Segmentation
Seiichiro Fukuda, Ryota Yoshihashi, Rei Kawakami +3
Multi-task learning improves generalization performance by sharing knowledge among related tasks. Existing models are for task combinations annotated on the same dataset, while the…
Differentiating Objects by Motion: Joint Detection and Tracking of Small Flying Objects
Ryota Yoshihashi, Tu Tuan Trinh, Rei Kawakami +3
While generic object detection has achieved large improvements with rich feature hierarchies from deep nets, detecting small objects with poor visual cues remains challenging. Moti…