About


Yikai Wang is a Postdoctoral Research Fellow at the MMLab@NTU, working with Prof. Chen Change Loy, affiliated with S-Lab, Nanyang Technological University, Singapore. He obtained his Ph.D. in Statistics at Fudan University in 2024, advised by Prof. Yanwei Fu. Prior to this, He completed B.S. in Mathematics at Fudan University in 2019. His research spans statistical machine learning, computer vision, and foundation models, with a focus on content creation, multi-modal models and sample selection.

Always available with yi-kai.wang@outlook.com, please let me know who you are.
My Fudan email is no longer active.

News



Research


Talks


Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model.
[slides] [Bilibili video (in Chinese, starts at 1:18:40)]
Oral presentation at Pre-CVPR@Shanghai, 2024.05.

Advancing Image Inpainting: From Versatility to Consistency.
[slides]
S-Lab at Nanyang Technological University, 2024.04.

Clean Sample Selection Algorithms with Statistical Sparsity Analysis.
[slides]
EML Munich Group at Technical University of Munich, 2024.03;
MLCV Group at Institute of Science and Technology Austria, 2024.04.

Few-shot Learning by Statistical Methods.
[slides]
CVPR 2023 tutorial, 2023.06:
Few-shot Learning from Meta-Learning, Statistical Understanding to Applications.

Sparse Learning for Noisy Data Detection.
[Youtube][Bilibili][slides]
CVPR 2022 tutorial, 2022.06:
Sparse Learning in Neural Networks and Robust Statistical Analysis.

Datasets


ReS for subject repositioning.
[paper] [intro] [dataset]
A benchmark dataset includes 100 paired images, featuring a repositioned subject while the other elements remain constant.

MISATO for image inpainting.
[arxiv] [intro] [dataset]
An evaluation dataset for indoor, outdoor landscape, building, and background inpainting.

FaceSketches-HairStyle40 for sketch2face generation.
[dataset]
A fine-grained Freehand Face Sketch dataset that features various hairstyles.

Publications


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

Content Creation

Repositioning the Subject within Image.
[arxiv] [full-size PDF] [intro] [code & ReS dataset] [demo: Youtube, Bilibili]
Yikai Wang, Chenjie Cao, Ke Fan, Qiaole Dong, Yifan Li, Xiangyang Xue, Yanwei Fu†.
TMLR, 2024.

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model.
[arxiv] [paper] [code] [intro]
Chenjie Cao, Yunuo Cai, Qiaole Dong, Yikai Wang, Yanwei Fu†.
CVPR, 2024.

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.

3D StreetUnveiler with Semantic-Aware 2DGS.
[arxiv] [code] [intro]
Jingwei Xu, Yikai Wang, Yiqun Zhao, Yanwei Fu, Shenghua Gao†.
Preprint, 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.

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†.
Technical Report, 2023.

Multi-modal Models

Unified Lexical Representation for Interpretable Visual-Language Alignment.
[arxiv] [code] [intro]
Yifan Li, Yikai Wang†, Yanwei Fu, Dongyu Ru, Zheng Zhang, Tong He†.
NeurIPS, 2024.

NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation.
[arxiv] [paper] [code] [intro]
Jingyang Huo*, Yikai Wang*, Yun Wang*, Xuelin Qian, Chong Li, Yanwei Fu†, Jianfeng Feng.
ECCV, 2024.

LEA: Learning Latent Embedding Alignment Model for fMRI Decoding and Encoding.
[arxiv]
Xuelin Qian*, Yikai Wang*, Xinwei Sun, Yanwei Fu, Xiangyang Xue, Jianfeng Feng†.
TMLR, 2024.

Sample Selection

Towards Global Optimal Visual In-Context Learning Prompt Selection.
[arxiv] [code]
Chengming Xu*, Chen Liu*, Yikai Wang†, Yuan Yao, Yanwei Fu.
NeurIPS, 2024.

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]
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]
Yikai Wang, Xinwei Sun, Yanwei Fu†.
CVPR, 2022.

How to Trust Unlabeled Data? Instance Credibility Inference for Few-Shot Learning.
[arxiv] [paper] [code] [intro]
Yikai Wang, Li Zhang, Yuan Yao†, Yanwei Fu†.
TPAMI. Accepted in 2021.

Instance Credibility Inference for Few-Shot Learning.
[arxiv] [paper] [code] [intro]
Yikai Wang, Chengming Xu, Chen Liu, Li Zhang, Yanwei Fu†.
CVPR, 2020.

Miscellaneous

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.

Education


Ph.D. in Statistics,
2019.09 - 2024.06, Fudan University.
B.S. in Mathematics,
2015.09 - 2019.06, Fudan University.

Experience


Postdoctoral Research Fellow,
2024.07 - present, Nanyang Technological University, Singapore.

Awards


Service


Teaching


Neural Network and Deep Learning,
TA, 2019-2022 Springs, Fudan University.

You are the -th visitor :)
Hosted on GitHub Pages. Theme modified from minimal and Jonbarron.