I am an Assistant Professor at ETH Zürich in Switzerland. I obtained my Ph.D. degree from Princeton University and became a postdoctoral researcher at UC Berkeley afterwards. I direct the Visual Intelligence and Systems (VIS) Group. I am a member of the Computer Vision Lab. My goal is to build perceptual systems capable of performing complex tasks in complex environments. My research is at the junction of machine learning, computer vision, and robotics. I currently work on the following topics:

• Representation Learning
• Algorithms for 2D and 3D motion analysis
• Real-world delivery of perception models
• Human machine collaboration for large-scale data exploration
• Policy learning for driving and manipulation
• Robot interaction in dynamic environments

I am currently looking for students with strong research records in computer science, electrical engineering, or mechanical engineering to join my group as Ph.D. students, postdoctoral researchers, or research interns. I also offer semester projects and master thesis advising to ETH students. To apply, please send me a cover letter and CV by email. I will usually reply within two weeks if there are suitable positions for the candidates.

Publications

	Xin Wang*, Thomas E. Huang*, Trevor Darrell, Joseph E. Gonzalez, Fisher Yu Frustratingly Simple Few-Shot Object Detection International Conference on Machine Learning, 2020 Paper Code
	Fisher Yu, Haofeng Chen, Xin Wang, Wenqi Xian, Yingying Chen, Fangchen Liu, Vashisht Madhavan, Trevor Darrell BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning Computer Vision and Pattern Recognition, 2020 Website Paper Data Code Scalabel Labeling Tool
	Yanzhao Zhou, Xin Wang, Jianbin Jiao, Trevor Darrell, Fisher Yu Learning Saliency Propagation for Semi-Supervised Instance Segmentation Computer Vision and Pattern Recognition, 2020 Paper Code
	Hou-Ning Hu, Qi-Zhi Cai, Dequan Wang, Ji Lin, Min Sun, Philipp Krähenbühl, Trevor Darrell, Fisher Yu Joint Monocular 3D Vehicle Detection and Tracking International Conference in Computer Vision, 2019 Paper Code
	Hang Gao, Huazhe Xu, Qi-Zhi Cai, Ruth Wang, Fisher Yu, Trevor Darrell Disentangling Propagation and Generation for Video Prediction International Conference in Computer Vision, 2019 Paper
	Bingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu, Jiashi Feng, Trevor Darrell Few-shot Object Detection via Feature Reweighting International Conference in Computer Vision, 2019 Paper Code
	Zhichao Yin, Trevor Darrell, Fisher Yu Hierarchical Discrete Distribution Decomposition for Match Density Estimation Computer Vision and Pattern Recognition, 2019 Paper Code
	Xin Wang, Fisher Yu, Ruth Wang, Trevor Darrell, Joseph E. Gonzalez TAFE-Net: Task-Aware Feature Embeddings for Efficient Learning and Inference Computer Vision and Pattern Recognition, 2019 Paper Code
	Xiangyu Chen, Xinlei Pan, Qi-Zhi Cai, John F. Canny, Fisher Yu Semantic Predictive Control for Explainable and Efficient Policy Learning International Conference on Robotics and Automation, 2019 Paper Video Code
	Dequan Wang, Coline Devin, Qi-Zhi Cai, Fisher Yu, Trevor Darrell Deep Object Centric Policies for Autonomous Driving International Conference on Robotics and Automation, 2019 Paper
	Xin Wang, Fisher Yu, Lisa Dunlap, Yi-An Ma, Ruth Wang, Azalia Mirhoseini, Trevor Darrell, Joseph E. Gonzalez Deep Mixture of Experts via Shallow Embedding Conference on Uncertainty in Artificial Intelligence, 2019 Paper
	Xin Wang, Fisher Yu, Zi-Yi Dou, Joseph E. Gonzalez SkipNet: Learning Dynamic Routing in Convolutional Networks European Conference on Computer Vision, 2018 Paper Code
	Chaowei Xiao, Ruizhi Deng, Bo Li, Fisher Yu, Mingyan Liu, Dawn Song Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation European Conference on Computer Vision, 2018 Paper
	Fisher Yu, Dequan Wang, Evan Shelhamer, Trevor Darrell Deep Layer Aggregation Computer Vision and Pattern Recognition, 2018 Paper Code
	Wenqi Xian, Patsorn Sangkloy, Varun Agrawal, Amit Raj, Jingwan Lu, Chen Fang, Fisher Yu and James Hays TextureGAN: Controlling Deep Image Synthesis with Texture Patches Computer Vision and Pattern Recognition, 2018 Paper
	Huiwen Chang, Jingwan Lu, Fisher Yu and Adam Finkelstein PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup Computer Vision and Pattern Recognition, 2018 Paper
	Xin Wang, Yujia Luo, Daniel Crankshaw, Alexey Tumanov, Fisher Yu, Joseph E. Gonzalez IDK Cascades: Fast Deep Learning by Learning not to Overthink Conference on Uncertainty in Artificial Intelligence, 2018 Paper
	Fisher Yu, Vladlen Koltun and Thomas Funkhouser Dilated Residual Networks Computer Vision and Pattern Recognition, 2017 Paper Code
	Shuran Song, Fisher Yu, Andy Zeng, Angel X. Chang, Manolis Savva and Thomas Funkhouser Semantic Scene Completion from a Single Depth Image Computer Vision and Pattern Recognition, 2017 Webpage Paper
	Huazhe Xu, Yang Gao, Fisher Yu and Trevor Darrell End-to-end Learning of Driving Models from Large-scale Video Datasets Computer Vision and Pattern Recognition, 2017 Paper
	Patsorn Sangkloy, Jingwan Lu, Chen Fang, Fisher Yu and James Hays Scribbler: Controlling Deep Image Synthesis with Sketch and Color Computer Vision and Pattern Recognition, 2017 Webpage Paper
	Jerry Liu, Fisher Yu and Thomas Funkhouser Interactive 3D Modeling with a Generative Adversarial Network International Conference on 3D Vision, 2017 Paper
	Judy Hoffman, Dequan Wang, Fisher Yu and Trevor Darrell FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation arXiv:1612.02649 cs.CV, 2016 Paper
	Fisher Yu and Vladlen Koltun Multi-Scale Context Aggregation by Dilated Convolutions International Conference on Learning Representations, 2016 Paper Code
	Huiwen Chang, Fisher Yu, Jue wang, Douglas Ashley and Adam Finkelstein Automatic Triage for a Photo Series ACM Transactions on Graphics (Proc. SIGGRAPH), 2016 Webpage Paper
	Manolis Savva, Fisher Yu, Hao Su, et al. SHREC’16 Track`: Large-Scale 3D Shape Retrieval from ShapeNet Core55 EuroGraphics SHREC2016 Workshop Report, 2016 Webpage Report
	Fisher Yu, Jianxiong Xiao and Thomas Funkhouser Semantic Alignment of LiDAR Data at City Scale Computer Vision and Pattern Recognition, 2015 Webpage Paper
	Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser and Jianxiong Xiao LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop arXiv:1506.03365 cs.CV, 2015 Webpage Paper Challenge
	Angel X. Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, Jianxiong Xiao, Li Yi, Fisher Yu ShapeNet: An Information-Rich 3D Model Repository arXiv:1512.03012 cs.GR, 2015 Webpage Paper
	Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang and Jianxiong Xiao 3D ShapeNets: A Deep Representation for Volumetric Shape Modeling Computer Vision and Pattern Recognition, 2015 Webpage Paper
	Fisher Yu and David Gallup 3D Reconstruction from Accidental Motion Computer Vision and Pattern Recognition, 2014 Webpage Paper Video Youtube code Bibtex
	Jingwan Lu, Fisher Yu, Adam Finkelstein and Stephen DiVerdi HelpingHand: Example-based Stroke Stylization ACM Transactions on Graphics (Proc. SIGGRAPH), 2012 Webpage Paper
	John P. Boyd and Fisher Yu Comparing Seven Spectral Methods for Interpolation and for Solving the Poisson Equation in a Disk: Zernike Polynomials, Logan-Shepp Ridge Polynomials, Chebyshev-Fourier Series, Cylindrical Robert Functions, Bessel-Fourier Expansions, Square-to-Disk Conformal Mapping and Radial Basis Functions Journal of Computational Physics, Volume 230, Issue 4, 2011 Paper

Students

Ph.D. students

• Xia Li
• Tobias Fischer

Services

• Organizer of Workshop on Autonomous Driving at CVPR 2017, 2018, 2019, 2020
• Organizer of Workshop on Machine Learning for Autonomous Driving at NeurIPS 2019
• Organizer of Workshop on Human In the Loop Learning (HILL) at ICML 2019
• Organizer of 3D Deep Learning Workshop at NIPS 2016
• Organizer of Large-scale Scene Understanding Challenge Workshop at CVPR 2016
• Organizer of CVPR 2016 tutorial on 3D Deep Learning with Marvin
• Organizer of Large-scale Scene Understanding Challenge Workshop at CVPR 2015

Tutorials

Here are the slides of the lectures on 3D reconstruction I gave in a seminar course in 2014. These lectures are intended for audience with no background knowledge in this area.