周吉喆, Ji-Zhe Zhou

周吉喆, Ji-Zhe Zhou

四川大学计算机学院副教授

Associate Professor at Sichuan University

GitHub Scholar Blog

周吉喆，四川大学计算机学院副教授， 四川省千人 IEEE TETCI 副主编 J. Imaging 客座主编，Eat More Group负责人，主要研究方向为伪造图像检测（Fake Image Detection）及生成与取证统一（Unified Generation and Forensics）。我主导开发了 IML-ViT SparseViT IMDL-BenCo ForensicHub 等多个开源基准项目，更多详情请见 GitHub 与 Google Scholar 主页。

I am an Associate Professor at the College of Computer Science, Sichuan University, and Sichuan Provincial Thousand Talents. I serve as Associate Editor of IEEE TETCI and Guest Editor of J. Imaging, and I lead the Eat More Group. My research focuses on Fake Image Detection and Unified Generation and Forensics. I have led the development of several open-source benchmark projects, including IML-ViT SparseViT IMDL-BenCo ForensicHub. For more details, please visit my GitHub and Google Scholar profiles.

♥ Special Thanks to Ms. Helen Wang. YY

News

Jul 2026

🏛️ Service Area Chair for NeurIPS Education Track.

Jul 2026

🏛️ Service Program Committee Member for ACM MM, NeurIPS, and AAAI.

Jun 2026

📄 CVPR 2026 RITA: Revisiting Image Manipulation Localization under Realistic Manipulation Scenarios. CVPR 2026.

May 2026

📄 Tech Report DeFakerOne: The first foundation model for unified fake image detection & localization, jointly developed with Ant Group Guangjian team.

May 2026

🏆 Award Gold Reviewer for ICML 2026.

May 2026

📄 ICML 2026 SICA: First monolithic FID model via semantic-induced constrained adaptation, outperforming 15 state-of-the-art methods.

Apr 2026

🏛️ Service Invited as Guest Editor of the special issue "Recent Advances in Multimedia Imaging and Content Security" for Journal of Imaging.

Apr 2026

🏆 Award DCIC 2026 Champion (1st / 173 teams) — 数字中国创新大赛 · 数据应用赛道：基于多模态大模型的场景文本图像伪造分析.

Selected Publications

SICA paper first page ICML'26
⭐ ICML 2026

Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction

Bo Du, Xiaochen Ma, Xuekang Zhu, Zhe Yang, Chaogun Niu, Chenfan Qu, Mingqi Fang, Zhenming Wang, Jingjing Liu, Jian Liu, Ji-Zhe Zhou

International Conference on Machine Learning (ICML), 2026

📄 Paper 💻 Code
RITA paper first page CVPR'26
⭐ CVPR 2026

Revisiting Image Manipulation Localization under Realistic Manipulation Scenarios

Xuekang Zhu, Ji-Zhe Zhou, Kaiwen Feng, Chenfan Qu, Xiwen Wang, Yunfei Wang, Liting Zhou, Jian Liu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

📄 Paper 💻 Code
IML-ViT paper first page arXiv

IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer

Xiaochen Ma, Bo Du, Zhuohang Jiang, Xia Du, Ahmed Y. Al Hammadi, Jizhe Zhou

arXiv preprint arXiv:2307.14863, 2023

📄 arXiv 💻 Code
ForensicHub paper first page NeurIPS'25
⭐ NeurIPS 2025

ForensicHub: Towards Universal Fake Image Detection and Localization

Bo Du, Xuekang Zhu, Xiaochen Ma, Chenfan Qu, Kaiwen Feng, Zhe Yang, Chi-Man Pun, Jian Liu, Ji-Zhe Zhou

Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2025

📄 Paper 💻 Code
SparseViT paper first page AAAI'25
⭐ AAAI 2025

Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Sparse-Coding Transformer

Lei Su, Xiaochen Ma, Xuekang Zhu, Chaoqun Niu, Zeyu Lei, Ji-Zhe Zhou

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025

📄 Paper 💻 Code
IMDL-BenCo paper first page NeurIPS'24
⭐ NeurIPS 2024 Spotlight

IMDL-BenCo: A Comprehensive Benchmark for Image Manipulation Detection & Localization

Xiaochen Ma, Xuekang Zhu, Lei Su, Bo Du, Zhuohang Jiang, Bingkui Tong, Zeyu Lei, Xinyu Yang, Chi-Man Pun, Jiancheng Lv, Jizhe Zhou

Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2024

📄 Paper 💻 Code
NCL-IML paper first page ICCV'23
⭐ ICCV 2023 Oral (Top 5%)

Pre-training-free Image Manipulation Localization via Non-Mutually Contrastive Learning

Jizhe Zhou, Xiaochen Ma, Xia Du, Ahmed Y. Alhammadi, Wentao Feng

IEEE/CVF International Conference on Computer Vision (ICCV), pp. 22346–22356, 2023

📄 Paper 💻 Code

Experience

2022 – Present

Associate Professor

Sichuan University, College of Computer Science

天府峨眉 援藏教师
Education

B.S., M.S., Ph.D.

University of Macau & The Chinese University of Hong Kong

Supervisor: Prof. Chi-Man Pun

Students & Alumni

Current Students 在读学生

杜博

Master · Intern @ 蚂蚁安全

优秀毕业论文

伪造图像检测

SICA ForensicHub IMDL-BenCo DeFakerOne DiffIML
牛超群

PhD @ NUS

CSC公派

生成与取证统一

Bones to Identity Boneprint SICA SparseViT
王汐文

PhD Student

硕博连读

生成与取证统一

dehallu3D RITA
何雨声

PhD Student

直博

生成与取证统一

CoSimUE
杨哲

Master Student

伪造图像检测

ForensicHub SICA DiffIML
周莉婷

Master Student

生成与取证统一

RITA
王韵菲

Master · Intern @ 腾讯混元

伪造图像检测

DiffIML
冯凯文

Master Student

伪造图像检测

ForensicHub SICA RITA
张皓为

Master · Intern @ 腾讯混元

生成与取证统一

FGM-HD
刘鑫

Master Student

伪造图像检测

DiffIML
张程洋

Master Student

伪造图像检测

李璐颖

Master Student

生成与取证统一

陈相羽

PhD Student

中核集团定培

缺陷检测

黄昱杰

Master Student

四川省公安厅定培

伪造图像检测

Alumni 已毕业学生

朱学康

Master → 蚂蚁安全

蚂蚁光鉴 Team Leader

生成与取证统一

RITA Mesorch ForensicHub IMDL-BenCo dehallu3D M³ DeFakerOne
马晓晨

PhD @ HKUST · Intern @ 腾讯混元 (Tencent Hunyuan)

优秀毕业论文

图像篡改检测

NCL-IML IML-ViT IMDL-BenCo
粟磊

Master → WPS武汉 (Kingsoft)

优秀毕业论文

图像篡改检测

SparseViT IMDL-BenCo
王坚

PhD → 中国公安部 (Ministry of Public Security, China)

公职

生成与取证统一

SLIT SQ-GAN
杨欣宇

Master @ Tsinghua

川大CCF学生主席 清华研究生院团委副书记

图像篡改检测

M³ IMDL-BenCo
雷泽宇

MSc @ USC (南加大)

吴玉章学院 澳门大学交换

图像篡改定位

IMDL-BenCo SparseViT Mesorch M³
张健

Master → 宁德时代 (CATL)

缺陷检测

倪睿洋

Master → 中国电信 (China Telecom)

因果推理

蒋卓航

PhD @ HKPolyU · Intern @ 快手 (Kuaishou)

计科之星

因果推理

Beyond Visual Appearances IMDL-BenCo
童炳魁

PhD @ MBZUAI

因果推理

Beyond Visual Appearances IMDL-BenCo
Eat More Group

Eat More Group

— Eat More · Play Smart —

Eat More Group Research Menu