Xiangyu Yue


Email: xyyue [at] berkeley [dot] edu

I am a Ph.D. student in Electrical Engineering and Computer Science at UC Berkeley, working with Prof. Alberto Sangiovanni Vincentelli and Prof. Kurt Keutzer. I study machine learning and computer vision.

Prior to UC Berkeley, I received my M.S. degree from Stanford University and B.S. degree from Nanjing University. I did internships at Google Research, Google [x] Robotics, Baidu AI Research, and Tencent AI Lab. I have received the Lotfi A. Zadeh Prize for my research work.

Google Scholar   |   GitHub   |   LinkedIn   |   Twitter

News


Selected Papers [ Full List ]


Self-Supervised Pretraining Improves Self-Supervised Pretraining
Colorado Reed*, Xiangyu Yue*, Ani Nrusimha, Sayna Ebrahimi, Vivek Vijaykumar, Richard Mao, Bo Li, Shanghang Zhang, Devin Guillory, Sean Metzger, Kurt Keutzer, Trevor Darrell (* indicates equal contribution)
Preprint 2021
PDF | Code | BibTex

Multi-source Few-shot Domain Adaptation
Xiangyu Yue, Zangwei Zheng, Colorado Reed, Hari Prasanna Das, Kurt Keutzer, Alberto Sangiovanni Vincentelli
In submission, NeurIPS 2021
PDF to come | Code to come | BibTex

Unsupervised Point Cloud Pre-Training via View-Point Occlusion, Completion
Hanchen Wang, Qi Liu, Xiangyu Yue, Joan Lasenby, Matthew J. Kusner
International Conference on Computer Vision (ICCV), 2021
PDF | Code | BibTex

On Ensemble Methods for Long-Tailed Recognition
Xiangyu Yue, Yang Zhang, Zhewei Yao, Sicheng Zhao, Kurt Keuzer, Alberto Sangiovanni Vincentelli, Boqing Gong
Preprint 2021
PDF | Code to come | BibTex

AugPrune: Robust Network Pruning via Augmented Data
Alex Zhao, Yaoqing Yang, Xiangyu Yue, Zhuang Liu, Elicia Ye, Michael Mahoney, Ramchandran Kannan, Joseph Gonzalez, Kurt Keutzer
Preprint 2021
PDF | Code to come | BibTex

Image2Point: 3D Point-Cloud Understanding with Pretrained 2D ConvNets
Chenfeng Xu, Shijia Yang, Bohan Zhai, Bichen Wu, Xiangyu Yue, Wei Zhan, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka
Preprint 2021
PDF | Code | BibTex

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
Xiangyu Yue*, Zangwei Zheng*, Shanghang Zhang, Yang Gao, Trevor Darrell, Kurt Keutzer, Alberto Sangiovanni-Vincentelli (* indicates equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021
PDF | Website | Code | Video | Poster | BibTex

Curriculum Cyclegan for Textual Sentiment Domain Adaptation with Multiple Sources
Sicheng Zhao*, Yang Xiao*, Jiang Guo*, Xiangyu Yue*, Jufeng Yang, Ravi Krishna, Pengfei Xu, Kurt Keutzer (* indicates equal contribution)
The Web Conference (WWW) 2021
PDF | Code | BibTex

Emotional Semantics-preserved and Feature-aligned CycleGAN for Visual Emotion Adaptation
Sicheng Zhao, Xuanbai Chen, Xiangyu Yue, Chuang Lin, Pengfei Xu, Ravi Krishna, Jufeng Yang, Guiguang Ding, Alberto Sangiovanni-Vincentelli, Kurt Keutzer
IEEE Transactions on Cybernetics (TCYB) 2021
PDF | BibTex

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Sicheng Zhao, Xiangyu Yue#, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E Gonzalez, Alberto L Sangiovanni-Vincentelli, Sanjit A Seshia, Kurt Keutzer (# indicates corresponding author)
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020
PDF | BibTex

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
Yang Zhang, Zixiang Zhou, Philip David, Xiangyu Yue, Zerong Xi, Boqing Gong, Hassan Foroosh
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020
PDF | Code | BibTex

Scenic: a Language for Scenario Specification and Scene Generation
Daniel J Fremont, Xiangyu Yue*, Tommaso Dreossi*, Shromona Ghosh*, Alberto L Sangiovanni-Vincentelli, Sanjit A Seshia (* indicates equal contribution)
ACM Conference on Programming Language Design and Implementation (PLDI) (2019)
PDF | Code (Scenic) | Code (Scenic2GTA) | BibTex

Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data
Xiangyu Yue, Yang Zhang, Sicheng Zhao, Alberto Sangiovanni-Vincentelli, Kurt Keutzer, Boqing Gong
International Conference on Computer Vision (ICCV), 2019
PDF | BibTex

Multi-source Domain Adaptation for Semantic Segmentation
Sicheng Zhao*, Bo Li*, Xiangyu Yue*, Yang Gu, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer (* indicates equal contribution)
Advances in Neural Information Processing Systems (NeurIPS) 2019
PDF | Code | BibTex

Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud
Bichen Wu*, Xuanyu Zhou*, Sicheng Zhao*, Xiangyu Yue, Kurt Keutzer (* indicates equal contribution)
International Conference on Robotics and Automation (ICRA) 2019
PDF | Code | BibTex

Counterexample-guided Data Augmentation
Tommaso Dreossi, Shromona Ghosh, Xiangyu Yue, Kurt Keutzer, Alberto Sangiovanni-Vincentelli, Sanjit A Seshia
International Joint Conference on Artificial Intelligence (IJCAI) 2018
PDF | Code | BibTex

Shift: A Zero-flop, Zero-parameter Alternative to Apatial Convolutions
Bichen Wu, Xiangyu Yue*, Alvin Wan*, Peter Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, Kurt Keutzer (* indicates equal contribution)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018
PDF | Code | BibTex

A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving
Xiangyu Yue, Bichen Wu, Sanjit A Seshia, Kurt Keutzer, Alberto L Sangiovanni-Vincentelli
International Conference on Multimedia Retrieval (ICMR) 2018
PDF | BibTex

Formal Specification for Deep Neural Networks
Sanjit A Seshia, Ankush Desai, Tommaso Dreossi, Daniel J Fremont, Shromona Ghosh, Edward Kim, Sumukh Shivakumar, Marcell Vazquez-Chanlatte, Xiangyu Yue
International Symposium on Automated Technology for Verification and Analysis (ATVA) 2018
PDF | BibTex

SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-time Road-object Segmentation from 3d LiDAR Point Cloud
Bichen Wu, Alvin Wan, Xiangyu Yue, Kurt Keutzer
International Conference on Robotics and Automation (ICRA) 2018
PDF | Video | Code | BibTex

Awards and Honors


Teaching


Website template courtesy