About

Yikai Wang is a Ph.D. candidate in Statistics under the supervision of Prof. Yanwei Fu at the School of Data Science, Fudan University. Prior to this, He completed B.S. in Mathematics from Fudan University.
His research ambitiously spans several areas, including statistical machine learning, computer vision, and foundation models. He has published 2 TPAMI, 4 CVPR, 1 ICCV and some other papers.

Always available to get in touch with yi-kai.wang@outlook.com, please let me know who you are.

Research

Sample Selection: [overview slides]
Trajectory: Small dataset → Noisy set recovery → Large scale dataset→ False-selection-rate control.
- Sparsity induced selection theory: noisy set recovery [ICI, TPAMI21], false-selection-rate control [Knockoffs-SPR, TPAMI23];
- Application: few-shot learning [ICI, CVPR20], learning with noisy labels [SPR, CVPR22], out-of-distribution detection [CVPR24];
Image Generation: [overview slides]
Trajectory: Enable non-text condition for frozen SD → Enable stable inpainting.
- Image inpainting: moving [SEELE, preprint], stable inpainting [ASUKA, preprint], multi-view inpainting [LeftRefill, CVPR24];
- Image editing: text-guided editing [SeMani, preprint];
Supervising/Collaborating Projects:
- fMRI-to-image decoding: latent alignment [preprint]; consistent decoding [NeuroPictor, preprint].
- Mask prediction: amodal segmentation [C2F-Seg, ICCV23];
- Data augmentation: FFD for oracle characters [ACCV22, final project of undergraduate course NNDL 2022, where I was TA.]

Talks

	Few-shot Learning by Statistical Methods. [slides] In CVPR 2023 tutorial with Prof. Yanwei Fu: Few-shot Learning from Meta-Learning, Statistical Understanding to Applications.
	Sparse Learning for Noisy Data Detection. [Youtube][Bilibili][slides] In CVPR 2022 tutorial: Sparse Learning in Neural Networks and Robust Statistical Analysis.

Publications

Arranged by topic and in chronological order. Updated list can be found at Google Scholar. (*): equal contribution; (†): corresponding author(s).

Sample Selection

	Test-Time Linear Out-of-Distribution Detection. [paper] Ke Fan, Tong Liu, Xingyu Qiu, Yikai Wang, Lian Huai, Zeyu Shangguan, Shuang Gou, Fengjian Liu, Yuqian Fu, Yanwei Fu, Xingqun Jiang. CVPR, 2024.
	Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels. [arxiv] [paper] [code] [intro] [简介] Yikai Wang, Yanwei Fu, Xinwei Sun†. TPAMI. Accepted in 2023.
	Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels. [arxiv] [paper] [code] [intro] [简介] Yikai Wang, Xinwei Sun, Yanwei Fu†. CVPR, 2022.
	How to Trust Unlabeled Data? Instance Credibility Inference for Few-Shot Learning. [arxiv] [paper] [code] [intro] [简介] Yikai Wang, Li Zhang, Yuan Yao†, Yanwei Fu†. TPAMI. Accepted in 2021.
	Instance Credibility Inference for Few-Shot Learning. [arxiv] [paper] [code] [intro] [简介] Yikai Wang, Chengming Xu, Chen Liu, Li Zhang, Yanwei Fu†. CVPR, 2020.

Image Generation

	LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model. [arxiv] [intro] Chenjie Cao, Yunuo Cai, Qiaole Dong, Yikai Wang, Yanwei Fu†. CVPR, 2024.
	Towards Context-Stable and Visual-Consistent Image Inpainting. [arxiv] [full-size PDF] [intro] [MISATO dataset] [demo: Youtube, Bilibili] Yikai Wang, Chenjie Cao, Ke Fan, Xiangyang Xue, Yanwei Fu†. Preprint, 2023.
	Repositioning the Subject within Image. [arxiv] [full-size PDF] [intro] [ReS dataset] [demo: Youtube, Bilibili] Yikai Wang, Chenjie Cao, Ke Fan, Qiaole Dong, Yifan Li, Xiangyang Xue, Yanwei Fu†. Preprint, 2023.
	Entity-Level Text-Guided Image Manipulation. [arxiv] [full-size PDF] [code] [intro] [demo: Youtube, Bilibili] Yikai Wang, Jianan Wang, Guansong Lu, Hang Xu, Zhenguo Li, Wei Zhang, Yanwei Fu†. Preprint, 2023.

Supervising/Collaborating Projects

	Coarse-to-Fine Amodal Segmentation with Shape Prior. [arxiv] [paper] [code] [intro] Jianxiong Gao, Xuelin Qian†, Yikai Wang, Tianjun Xiao†, Tong He, Zheng Zhang, Yanwei Fu. ICCV, 2023.
	NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation. [arxiv] [intro] Jingyang Huo, Yikai Wang**, Xuelin Qian, Yun Wang, Chong Li, Jianfeng Feng, Yanwei Fu†. Preprint, 2023.
	LEA: Learning Latent Embedding Alignment Model for fMRI Decoding and Encoding. [arxiv] Xuelin Qian, Yikai Wang**, Xinwei Sun, Yanwei Fu, Xiangyang Xue, Jianfeng Feng†. Preprint, 2023.
	FFD Augmentor: Towards Few-Shot Oracle Character Recognition from Scratch. [paper] [code] Xinyi Zhao, Siyuan Liu, Yikai Wang, Yanwei Fu†. ACCV, 2022. Note: This is the final project of undergraduate course NNDL 2022, for which I served as TA.
	An Embarrassingly Simple Baseline to One-Shot Learning. [paper] Chen Liu, Chengming Xu, Yikai Wang, Li Zhang, Yanwei Fu†. CVPR Workshop, 2020.

Awards

Outstanding Graduates, Shanghai, 2024. (Top 2 Ph.D. graduates in our school) Will receive official recognition if i successfully graduate in 2024 :)
Outstanding Freshmen, Fudan University, 2015. (Top 0.02% in Gaokao, the National Higher Education Entrance Examination in China.)

Service

I have served as a reviewer for conferences and journals, some of which are listed below:
- IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2023, 2024
- International Conference on Computer Vision (ICCV) 2023
- European Conference on Computer Vision (ECCV) 2024
- International Conference on Machine Learning (ICML) 2023, 2024
- Conference on Neural Information Processing Systems (NeurIPS) 2022 (top 8% reviewer), 2023
- International Conference on Learning Representations (ICLR) 2024
- IEEE Transactions on Image Processing (TIP) from 2024
- Transactions on Machine Learning Research (TMLR) from 2023

Teaching

Neural Network and Deep Learning,

TA, 2019-2022 Springs, Fudan University.

Timeline

Ph.D. in Statistics,

2019.9 - present, Fudan University.

B.S. in Mathematics,

2015.9 - 2019.6, Fudan University.