450 citations
- The University of TokyoJP19 papers
- Kyoto UniversityJP6 papers
- RIKEN Center for Advanced Intelligence ProjectJP5 papers
- National Institute of InformaticsJP4 papers
- RIKENJP3 papers
- Tohoku UniversityJP3 papers
- University of TsukubaJP3 papers
- Johns Hopkins UniversityUS2 papers
- Keio UniversityJP2 papers
- Kobe UniversityJP2 papers
- Massachusetts Institute of TechnologyUS2 papers
- Nara Institute of Science and TechnologyJP2 papers
12 papers · 1 filter
Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
He Huang, Shunta Saito, Yuta Kikuchi +3
Scene graph parsing aims to detect objects in an image scene and recognize their relations. Recent approaches have achieved high average scores on some popular benchmarks, but fail…
Label-Efficient Multi-Task Segmentation using Contrastive Learning
Junichiro Iwasawa, Yuichiro Hirano, Yohei Sugawara
Obtaining annotations for 3D medical images is expensive and time-consuming, despite its importance for automating segmentation tasks. Although multi-task learning is considered an…
An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation
Yuta Tokuoka, Shuji Suzuki, Yohei Sugawara
With recent advances in supervised machine learning for medical image analysis applications, the annotated medical image datasets of various domains are being shared extensively. G…
Fast Soft Color Segmentation
Naofumi Akimoto, Huachun Zhu, Yanghua Jin +1
We address the problem of soft color segmentation, defined as decomposing a given image into several RGBA layers, each containing only homogeneous color regions. The resulting laye…
Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval
Shuhei Yokoo, Kohei Ozaki, Edgar Simo-Serra +1
We propose an efficient pipeline for large-scale landmark image retrieval that addresses the diversity of the dataset through two-stage discriminative re-ranking. Our approach is b…
Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects
Yusuke Niitani, Takuya Akiba, Tommi Kerola +3
Efficient and reliable methods for training of object detectors are in higher demand than ever, and more and more data relevant to the field is becoming available. However, large d…