Can Qin's Homepage

About Me

I am a AI Research Scientist at Salesforce Research. I completed Ph.D. at Northeastern University (NEU) and obtained B.E. degree from Xidian University (XDU). My research interests broadly include the theories and applications in machine learning, computer vision and data mining, with the high focus on multi-modal and generative ai.

News

2023.11: Begin my journey in Salesforce Research at Palo Alto, CA.
2023.07: UniControl Huggingface Space is open to public! Welcome to play with it.
2023.07: Our GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation paper is accepted by ICCV 23.
2023.07: I have presented our Unified Controllable Image Generation paper in AI Open Courses . Many thanks to ZHIDX.com!
2023.06: I have passed the PhD Dissertation Defense and become Dr. Qin!
2023.05: Our Unified Controllable Image Generation paper is uploaded to arXiv. Code is public now.
2023.05: We have one paper for trustworthy face verification accepted by TIP. Congrats to Joe.
2023.04: We have one paper for efficient and lightweight image super-resolution accepted by TPAMI. Congrats to Huan and Yulun.
2023.02: We have one paper for open-vocabulary instance segmentation accepted by CVPR 2023. Congrats to Vibashan.
2023.01: We have one paper accepted by ICLR 2023 as Oral presentation (Notable Top 5%). Congrats to Xu.
2022.09: One paper is accepted by ICDM 2022 and one paper is accepted by IEEE Transactions on Image Processing (TIP).
2022.08: I have been invited as a PC member for AAAI 2023 and a reviewer for ICLR 2023 .
2022.08: We have two papers accepted by CIKM 2022.
2022.05: We have a paper accepted by KDD 2022. Thanks to all the mentors from Adobe Research.
2022.05: I start my summer internship at Salesforce Research at Palo Alto, CA.
2022.04: We have two papers accepted by IJCAI 2022.
2022.02: The official code of PointMLP is released. I have been invited as the reviewer for TPAMI and TMLR.
2022.01: We have two papers accepted by ICLR 2022. Congrats to Xu and Yulun.
2022.01: I have been invited as a reviewer for ICML 2022 .
2021.12: The manuscript of our new paper - Semi-supervised Domain Adaptive Structure Learning has been uploaded.
2021.11: I have been invited as a reviewer for CVPR 2022 and TNNLS .
2021.11: Our paper about AI + Science (i.e., Topology Optimization) has been accepted by Nature Communications .
2021.10: Our new paper - AdaMomentum for a general-purpose deep learning optimizer has been uploaded.
2021.09: We have two papers accepted by NeurIPS 2021, with one Poster and one Spotlight respectively.
2021.09: We have a paper accepted by IEEE Transactions on Image Processing (TIP) .
2021.08: We have a paper accepted by International Conference on Data Mining (ICDM) 2021 .
2021.07: We have a paper accepted by International Conference on Computer Vision (ICCV) 2021 .
2021.07: I have been invited as a program committee (PC) member for IJCAI 2022 .
2021.07: Our paper is accepted by ACM Multimedia (MM) 2021 .
2021.06: I have been invited as a reviewer for ICLR 2022 .
2021.04: I have received the SIAM Student Travel Award to support the paper presentation at SDM 2021.
2021.04: I have been invited as a reviewer for NeurIPS 2021.
2021.03: Our journal extension of the unbiased Face Recognition paper is uploaded to the arXiv.
2021.03: Our new Neural Pruning survey paper is uploaded to the arXiv.
2021.03: I have been invited as a reviewer for IEEE Robotics and Automation Letters (RA-L) .
2021.02: I have been invited as a reviewer for ICCV 2021.
2021.01: I have been invited as a reviewer for IEEE Transactions on Image Processing (TIP) .
2021.01: Our Neural Pruning paper is accepted by ICLR 2021 as Poster.
2020.12: Our Semi-supervised DA paper is accepted as a regular paper by SDM 2021 .
2020.12: Our new Face Synthesis paper is uploaded to the arXiv.
2020.12: I will start my 2021 summer intern at Adobe Research remotely.
2020.12: I have been invited as a reviewer for CVPR 2021 .
2020.11: I have been promoted as a senior program committee (SPC) member for IJCAI 2021 .
2020.09: I have been invited as a program committee (PC) member for AAAI 2021 .
2020.08: I have been invited as a program committee (PC) member for IJCAI 2021 .
2020.07: Our paper is accepted by ECCV 2020 as Poster.
2020.05: Our paper is accepted by CVPR Workshop on Fair, Data Efficient and Trusted Computer Vision, 2020.
2019.12: I have been invited as a program committee (PC) member for IJCAI-PRICAI 2020 .
2019.11: Our paper is accepted by AAAI 2020 as Poster.
2019.10: Our paper is awarded as the Best Paper of ICCV Workshop on RLQ, 2019.
2019.09: Our paper is accepted by NeurIPS 2019 as Poster.
2019.08: Our paper is accepted by ICCVW on RLQ, 2019 as Oral.
2019.06: Start my internship at Adobe in San Jose.
2018.09: Begin my journey in Smile Lab, Northeastern University at Boston.

Experiences

SMILE Lab, Northeastern University, Boston, USA Research Assistant, Sep. 2018 ~ June 2023 Advisor: Prof. Yun Raymond Fu
Salesforce Research, Palo Alto, USA Research Intern, May 2022 ~ June 2023 Mentors: Dr. Ning Yu, Dr. Chen Xing, Dr. Shu Zhang, Dr. Zeyuan Chen, Prof. Stefano Ermon, Dr. Caiming Xiong, and Dr. Ran Xu
Adobe Research, San Jose, USA Research Intern, June 2021 ~ Sep. 2021 Mentors: Dr. Sungchul Kim, Dr. Handong Zhao, Dr. Tong Yu and Dr. Ryan Rossi
Adobe, San Jose, USA Data Science Intern, June 2019 ~ Aug. 2019 Mentors: Dr. Jie Zhang, Dr. Yiwen Sun and Dr. Bo Peng
OMEGA Lab, Xidian University, Xi'an, China Visiting Research Assistant, Sep. 2017 ~ June 2018 Mentors: Prof. Maoguo Gong and Prof. Yue Wu

Pre-print Papers

HIVE: Harnessing Human Feedback for Instructional Visual Editing
Shu Zhang*, Xinyi Yang*, Yihao Feng*, Can Qin, Chia-Chih Chen, Ning Yu, Zeyuan Chen, Huan Wang, Silvio Savarese, Stefano Ermon, Caiming Xiong and Ran Xu
arXiv:2303.09618.
[arXiv] [Code]

Selected Conference Papers

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Can Qin, Shu Zhang, Ning Yu, Yihao Feng, Xinyi Yang, Yingbo Zhou, Huan Wang, Juan Carlos Niebles, Caiming Xiong, Silvio Savarese, Stefano Ermon, Yun Fu, and Ran Xu
Advances in Neural Information Processing Systems (NeurIPS), 2023. (to appear)
[arXiv] [Code] [HF Space] [Website] [Press]

Rethinking Adam: A Twofold Exponential Moving Average Approach
Yizhou Wang, Yue Kang, Can Qin, Huan Wang, Yi Xu, Yulun Zhang and Yun Fu
IEEE International Conference on Data Mining (ICDM), 2023. (to appear)
[arXiv] [Code]

GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
Can Qin, Ning Yu, Chen Xing, Shu Zhang, Zeyuan Chen, Stefano Ermon, Yun Fu, Caiming Xiong and Ran Xu
International Conference on Computer Vision (ICCV), 2023. (to appear)
[arXiv] [Code] [Website]

Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations
Vibashan VS, Ning Yu, Chen Xing, Can Qin, Mingfei Gao, Juan Carlos Niebles, Vishal M. Patel and Ran Xu
Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[Paper] [Code]

Image as Set of Points
Xu Ma, Yuquan Zhou, Huan Wang, Can Qin, Bin Sun, Chang Liu and Yun Fu
International Conference on Learning Representations (ICLR), 2023. (Oral, notable top 5%)
[Paper] [Code]

Making Reconstruction-based Method Great Again for Video Anomaly Detection
Yizhou Wang, Can Qin, Yue Bai, Yi Xu, Xu Ma, Yun Fu
IEEE International Conference on Data Mining (ICDM), 2022.
[Paper] [Code]

Robust Semi-supervised Domain Adaptation against Noisy Labels
Can Qin, Yizhou Wang, Yun Fu
ACM International Conference on Information and Knowledge Management (CIKM), 2022.
[Paper] [Code]

Self-supervision Meets Adversarial Perturbation: A Novel Framework for Anomaly Detection
Yizhou Wang, Can Qin, Rongzhe Wei, Yi Xu, Yue Bai, Yun Fu
ACM International Conference on Information and Knowledge Management (CIKM), 2022.
[Paper] [Code]

External Knowledge Infusion for Tabular Pre-training Models with Dual-adapters
Can Qin, Sungchul Kim, Handong Zhao, Tong Yu, Ryan Rossi, Yun Fu
ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2022.
[Paper] [Code]

Emerging Paradigms of Neural Network Pruning
Huan Wang, Can Qin, Yue Bai, Yulun Zhang, Yun Fu
International Joint Conference on Artificial Intelligence (IJCAI), 2022.
[arXiv] [Code]

Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
Xu Ma, Can Qin, Haoxuan You, Haoxi Ran and Yun Fu
International Conference on Learning Representations (ICLR), 2022.
[Paper] [Code]

Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation
Can Qin, Handong Zhao, Lichen Wang, Huan Wang, Yulun Zhang and Yun Fu
Advances in Neural Information Processing Systems (NeurIPS), 2021.
[Paper] [Code]

Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
Yulun Zhang*, Huan Wang*, Can Qin and Yun Fu
Advances in Neural Information Processing Systems (NeurIPS), 2021. (Spotlight, 3%)
[Paper] [Code]

Neural Pruning via Growing Regularization
Huan Wang, Can Qin, Yulun Zhang, Yun Fu
International Conference on Learning Representations (ICLR), 2021.
[Paper] [arXiv] [Code] [BibTex]

Contradictory Structure Learning for Semi-supervised Domain Adaptation
Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu
SIAM International Conference on Data Mining (SDM), 2021.
[Paper] [arXiv] [Code] [BibTex]

PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
Can Qin*, Haoxuan You*, Lichen Wang, C.-C. Jay Kuo, Yun Fu. (* equal contribution)
Advances in Neural Information Processing Systems (NeurIPS), 2019.
[Paper] [Code] [BibTex]

Generatively Inferential Co-Training for Unsupervised Domain Adaptation
Can Qin, Lichen Wang, Yulun Zhang, Yun Fu.
ICCV Workshop on Real-World Recognition from Low-Quality Images and Videos, 2019. (Best Paper Award )
[Paper] [BibTex]

full papers

Journal Papers

Balancing Biases and Preserving Privacy on Balanced Faces in the Wild
Joseph Robinson, Can Qin, Yann Heno, Samson Timoner, Yun Fu
IEEE Transactions on Image Processing (TIP), 2023. (to appear)
[Paper] [arXiv] [Code]

Global Aligned Structured Sparsity Learning for Efficient Image Super-Resolution
Huan Wang*, Yulun Zhang*, Can Qin, Luc Van Gool, Yun Fu
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023.
[Paper]

Semi-supervised Domain Adaptive Structure Learning
Can Qin, Lichen Wang, Qianqian Ma, Yu Yin, Huan Wang, Yun Fu
IEEE Transactions on Image Processing (TIP), 2022.
[Paper] [arXiv] [Code]

Self-Directed Online Machine Learning for Topology Optimization
Changyu Deng, Yizhou Wang, Can Qin, Yun Fu, Wei Lu
Nature Communications (Nature Comm), 2022.
[Paper] [Press]

Awards

SIAM Student Travel Award, 2021
Best Paper Award of ICCV Workshop on RLQ, 2019
The Star of Graduates in Class 2018 (Highest Honor in XDU), 2018
The First Prize Scholarship in XDU, 2016, 2017
Meritorious Winner of the Interdisciplinary Contest in Modeling, 2016
Outstanding Student Leader in XDU, 2015

Professonal Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Reviewer

Transactions on Machine Learning Research (TMLR), Reviewer

ACM Transactions on Knowledge Discovery from Data (TKDD), Reviewer

IEEE Robotics and Automation Letters (RA-L), Reviewer

IEEE Transactions on Image Processing (TIP), Reviewer

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Reviewer

IEEE Computational Intelligence Magazine, External Reviewer

International Joint Conference on Artificial Intelligence (IJCAI), PC Member

AAAI Conference on Artificial Intelligence (AAAI), PC Member

Conference on Neural Information Processing Systems (NeurIPS), Reviewer

International Conference on Learning Representations (ICLR), Reviewer

International Conference on Machine Learning (ICML), Reviewer

The Conference on Computer Vision and Pattern Recognition (CVPR), Reviewer

International Conference on Computer Vision (ICCV), Reviewer

European Conference on Computer Vision (ECCV), Reviewer

IEEE International Conference on Automatic Face and Gesture Recognition (FG), Reviewer

5th Recognizing Families In the Wild (RFIW), [White Paper Link], with FG21, Program Co-Chair

Talks

[07/18/2023] Multi-modal X-to-image Generation @ JingDong Health

[07/14/2023] Unified Controllable Image Generation and Editing @ ZHIDX.com AI Open Course

[06/06/2023] Unified Controllable Image Generation and Editing @ JingDong Health

[08/17/2022] KDD Oral @ DC Convention Center

[09/30/2021] Data Lab @ NEU

Project Demos

Project: Optical Character Recognition (OCR) for Banner Images
Tools: Tesseract OCR, OpenCV
Methods: EAST (Text Localization), LSTM (Text Recognition)
Pipeline: RGB -> Gray -> Gaussian Filtering -> Binarization -> OCR
Full Demo: Link

Programming Skills

Language: Python, MATLAB, C/C++, LATEX, Markdown and others.

Machine Learning Frameworks: PyTorch, TensorFlow, Keras, PyG, AllenNLP, Sklearn, OpenCV and others.