A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation
- Tomoya Sakai
- Haoxiang Qiu
- et al.
- 2024
- NeurIPS 2024
Bio
Haxiang Qiu (shota) is a machine learning researcher at IBM Research - Tokyo. He received his Master degree of engineering from Waseda University. His research interests include machine learning, artificial intelligence. especially in computer vision involving deep neural networks.
Publications
Simple Class Relation Helps Generalized Few-Shot Semantic Segmentation
- Tomoya Sakai
- Haoxiang Qiu
- et al.
- 2024
- MIRU 2024
Domain Adaptation from Sequentially Arriving Target Images with Online Deep Sets
- 2024
- MIRU 2024
Domain-adaptive Instance Segmentation for Visual Inspection from Civil Infrastructure Images
- 2024
- MIRU 2024
Probabilistic feature matching for fast scalable visual prompting
- Thomas Frick
- Cezary Skura
- et al.
- 2024
- IJCAI 2024
Interactive Image Segmentation Guided by Visual Prompting
- Thomas Frick
- Cezary Skura
- et al.
- 2024
- CVPR 2024
A cycle consistency based Approach for Semantic Segmentation on crack images
- Haoxiang Qiu
- Tomoya Sakai
- et al.
- 2024
- SSII 2024
Preventing Catastrophic Forgetting in Generalized Few-Shot Semantic Segmentation
- 2024
- JSAI 2024
Visual-Text Prompting
- 2024
- JSAI 2024
Simple Yet Effective Approach to Generalized Few-Shot Semantic Segmentation
- 2023
- IBISML 2023
Patents
Projects
Visual Prompting
Using AI to build computer vision models within minutes, through quick intuitive prompts, and with just a few images
Top collaborators
TK
Takayuki Katsuki
Researcher
TS
TO
Takayuki Osogami
Senior Technical Staff Member
DK
Daiki Kimura
Senior Research Scientist & Manager / Master Inventor