I am currently a research scientist at Cyberagent AI Lab, and a project researcher with The University of Tokyo, Japan. I am a member of Aizawa Labratory and working with Prof. Kiyoharu Aizawa.
My research interest is in Computer Vision, including Image Generation, Visual Understanding and Training Data Synthesis.
News
- 2024.07: 🎉🎉 2 papers are accpeted by ECCV 2024
Publications
ECCV 2024
The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization
Jiafeng Mao, Xueting Wang, Kiyoharu Aizawa
- Collecting noise pixel blocks to construct initial noise according to specified layout.
- Comfirming versatility of noise blocks over prompts and images.
ACM MM 2023
Guided Image Synthesis via Initial Image Editing in Diffusion Model
Jiafeng Mao, Xueting Wang, Kiyoharu Aizawa
- Analyzing the generation tendency of intial noise
- initial noise manipulation for generated image repainting and layout-to-image generation
- Dealing with Synthetic Data Contamination in Online Continual Learning, Maorong Wang, Nicolas Michel, Jiafeng Mao and Toshihiko Yamasaki. NeurIPS 2024
- SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning, Zerun Wang, Liuyu Xiang, Lang Huang, Jiafeng Mao, Ling Xiao and Toshihiko Yamasaki.ECCV 2024
- Noise-Avoidance Sampling for Annotation Missing Object Detection, Jiafeng Mao, Qing Yu, Irie Go and Kiyoharu Aizawa. ICIP 2023
- Training-Free Location-Aware Text-to-Image Synthesis, Jiafeng Mao, Xueting Wang.ICIP 2023(Oral)
- Noisy Annotation Refinement for Object Detection, Jiafeng Mao, Qing Yu, Yoko Yamakata and Kiyoharu Aizawa. BMVC 2021
- Noisy Localization Annotation Refinement for Object Detection, Jiafeng Mao, Qing Yu and Kiyoharu Aizawa. ICIP2020(Oral)
arXiv Papers
- Training-Free Sketch-Guided Diffusion with Latent Optimization, Sandra Zhang Ding, Jiafeng Mao, Kiyoharu Aizawa.
- Training Data Synthesis with Difficulty Controlled Diffusion Model, Zerun Wang, Jiafeng Mao, Xueting Wang, Toshihiko Yamasaki
- From Obstacles to Resources: Semi-supervised Learning Faces Synthetic Data Contamination, Zerun Wang, Jiafeng Mao, Liuyu Xiang, Toshihiko Yamasaki
- Reward Incremental Learning in Text-to-Image Generation, Maorong Wang, Jiafeng Mao, Xueting Wang, Toshihiko Yamasaki
Honors and Awards
- 2025 Reviewer for CVPR 2025, ICCV 2025, ACM MM 2025, WACV 2025, ICME 2025, MIRU 2025
- 2024 Reviewer for CVPR 2024, ECCV 2024, ACM MM 2024, MIRU 2024
- 2022 IST-RA: A Doctoral Student Special Incentives Program provided by the University of Tokyo Graduate School of Information Science and Technology.
- 2020 Kaggle Global Wheat Detection Competition Silver Medal.
- 2020 MIRU Student Encouragement Award