Home People Research Publications Demos
         
News Jobs Prospective
Students
About Internal

Pei Wang

Pei Wang

Majoring in Machine Learning and Data Science,
University of California, San Diego

Email: pew062@eng.ucsd.edu


Bio:

I am a Ph.D. candidate advised by professor Nuno Vasconcelos, working on machine learning, deep learning and their applications on computer vision, more specifically on explainable AI, visualization, image generation and synthesis, object detection, domain adaptation, machine teaching for scalable learning, stylization, etc.

News:

One paper was accepted to T-PAMI.

One paper was accepted to CVPR 2022.

One paper was accepted to ICCV 2021.

Four papers were accepted to CVPR 2021, three first-author papers and one oral.

I will intern at Amazon AWS in summer 2021.

Representative Publications:

A Generalized Explanation Framework for Visualization of Deep Learning Model Predictions
Pei Wang, and Nuno Vasconcelos
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023
[ code| poster| paper| supp| BibTex ]

Omni-DETR: Omni-Supervised Object Detection with Transformers
Pei Wang, Zhaowei Cai, Hao Yang, Gurumurthy Swaminathan, Nuno Vasconcelos, Bernt Schiele, Stefano Soatto
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
New Orleans, 2022
[ code| poster| paper| supp| BibTex ]

A Machine Teaching Framework for Scalable Recognition
Pei Wang, Nuno Vasconcelos
IEEE International Conference on Computer Vision (ICCV)
Virtual, 2021
[ code| poster| paper| supp | BibTex ]

Gradient-Based Algorithms for Machine Teaching
Pei Wang, Kabir Nagrecha, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Virtual, 2021
[ code | poster | paper | supp | BibTex ]

Rethinking and Improving the Robustness of Image Style Transfer
Pei Wang, Yijun Li, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Virtual, 2021 (Oral presentation & Best Paper Candidate)
[ code | poster| paper | BibTex ]

IMAGINE: Image Synthesis by Image-Guided Model Inversion
Pei Wang, Yijun Li, Krishna Kumar Singh, Jingwan Lu, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Virtual, 2021
[ code | poster | paper | BibTex ]

SCOUT: Self-aware Discriminant Counterfactual Explanations
Pei Wang and Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Seattle, Washington, United States, 2020
[ code | poster | paper | BibTex ]

Deliberative Explanations: visualizing network insecurities
Pei Wang and Nuno Vasconcelos
Conference on Neural Information Processing Systems (NeurIPS)
Vancouver, Canada, 2019
[ code | poster | pdf | BibTex ]

Towards Realistic Predictors
Pei Wang and Nuno Vasconcelos
European Conference on Computer Vision (ECCV)
Munich, Germany, 2018 (Oral presentation)
[ code | poster | pdf | BibTex ]

Graph Based Skeleton Motion Representation and Similarity Measurement for Action Recognition
Pei Wang, Chunfeng Yuan, Weiming Hu, Bing Li and Yanning Zhang
European Conference on Computer Vision (ECCV)
Amsterdam, the Netherlands, 2016
[ project | ps | pdf | BibTex ]

Professional Experience:

University of California, San Diego
Graduate Student Researcher
San Diego, United States, 2017-Now

Adobe Research
Intern Research Scientist
Seattle, United States, Summer 2020

Amazon AWS
Applied Scientist Intern
Virtual, United States, Summer 2021

Awards:

UCSD ECE department FellowShip, Sep 2017

National Scholarship, Nov 2013

National Scholarship, Nov 2012

Last update: Dec, 2021





© SVCL