Representative Work

 

Deep Learning


DSN
Chen-Yu Lee*, Saining Xie*, Patrick Gallagher, Zhengyou Zhang, and Zhuowen Tu, "Deeply-Supervised Nets", AISTATS, 2015. (*equal contribution) (pdf) (an early arxiv version, oral at NIPS14 Deep Learning Workshop) (project page)

HED




Saining Xie and Zhuowen Tu, "Holistically-Nested Edge Detection",  ICCV15
(Marr Prize Honorable Mention), arXiv:1504.06375, 2015. (trained models and code)

GPooling


Chen-Yu Lee, Patrick Gallagher, and Zhuowen Tu, "Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree", arXiv:1509.08985, 2015.

ConvPP

Saining Xie*, Xun Huang*, and Zhuowen Tu, "Convolutional Pseudo-Prior for Structured Labeling", arXiv:1511.07409, 2015. (*equal contribution)

GeneratorCNN
Patrick Gallagher, Shuai Tang, and Zhuowen Tu, "What Happened to My Dog in That Network: Unraveling Top-down Generators in Convolutional Neural Networks", arXiv:1511.07125, 2015.


Object Detection


ICF
Piotr Dollár, Zhuowen Tu, Pietro Perona, and Serge Belongie, "Integral Channel Features", Proc. of British Machine Vision Conference (BMVC), 2009 (pdf).


Cong Yao, Xiang Bai, Wenyu Liu, Yi Ma, and Zhuowen Tu, "Detecting Texts of Arbitrary Orientations in Natural Images", CVPR 2012. (pdf) (data)


 

Structured Prediction


Auto-Context

Quannan Li, Jingdong Wang, David Wipf, and Zhuowen Tu
Fixed-Point Model for Structured Labeling
International Conference on Machine Learning (ICML), 2013 (matlab code)

Zhuowen Tu and Xiang Bai
Auto-context and Its application to High-level Vision Tasks and 3D Brain Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(10), pp. 1744-1757, 2010. 
(source code included in the fixed-point package)
Also download the BrainParser (Windows and Linux) for segmenting anatomical  brain structures.

Zhuowen Tu
Auto-context and Its application to High-level Vision Tasks
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008


Hybrid DG

Zhuowen Tu, Katherin Narr, Piotr Dollar, Iov Dinov, Paul Thompson, and Arthur Toga
Brain Anatomical Structure Segmentation by Hybrid Discriminative/Generative Models
Transactions on Medical Imaging, vo. 27, no. 4, pp.495-508, 2008.
Download  the BrainParser (Windows and Linux) for segmenting anatomical brain structures (based on auto-context now).


Image Parsing

Zhuowen Tu, Xiangrong Chen, Alan Yuille, and Song-Chun Zhu
Image Parsing: Unifying Segmentation, Detection, and Object Recognition
International Journal of Computer Vision, vol. 63, no. 2, pp. 113-140, 2005


DDMCMC

Zhuowen Tu and Song-Chun Zhu
Image Segmentation by Data-Driven Markov Chain Monte Carlo
IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 5, May, 2002
Download the exectuable program.
Download the exectuable program and source code for a fast implementation based on SW-Cuts (cite paper).

 

 

Discriminative and Generaive Model Learning


GDL

Zhuowen Tu
Learning Generative Models via Discriminative Approaches
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2007


PBT

Zhuowen Tu
Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering
IEEE International Conference on Computer Vision (ICCV), 2005
Download the PBT-based BEL edge detector.




Weakly Supervised Visual Representation Construction

Xinggang Wang, Baoyuan Wang, Xiang Bai, Wenyu Liu, and Zhuowen Tu
Max-Margin Multiple Instance Dictionary Learning
International Conference on Machine Learning (ICML), 2013

Quannan Li, Jiajun Wu, and Zhuowen Tu
Harvesting Mid-level Visual Concepts from Large-scale Internet Images
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013 (project page)

Jun Zhu, Baoyuan Wang, Xiaokang Yang, Wenjun Zhang, and Zhuowen Tu
Action Recognition with Actons
IEEE International Conference on Computer Vision (ICCV), 2013


Jun-Yan Zhu, Jiajun Wu, Yichen Wei, Eric Chang, and Zhuowen Tu
Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning
IEEE Tran. PAMI, 2014
(short version appeared on CVPR
, 2012) (project page)

Xinggang Wang, Zhengdong Zhang, Yi Ma, Xiang Bai, Wenyu Liu, and Zhuowen Tu
Robust Subspace Discovery via Relaxed Rank Minimization
Neural Computation, 2014

Yan Xua, Jun-Yan Zhu, Eric I-Chao Chang, Maode Lai, and Zhuowen Tu
Weakly Supervised Histopathology Cancer Image Segmentation and Classification
Medical Image Analysis, 2014. (project page) (code)

Yan Xu*, Jun-Yan Zhu*, Eric Chang, and Zhuowen Tu (* indicates equal contributions)
Multiple Clustered Instance Learning for Histopathology Cancer Image Segmentation, Clustering, and Classification
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012


Piotr Dollar, Boris Babenko, Serge Belongie, Pietro Perona, and Zhuowen Tu
Multiple Component Learning for Object Detection
European Conference on Computer Vision (ECCV), 2008





 


 

Funding Supports:

NSF IIS-1618477
Northrop Grumman Contextual Robotics grants

NSF IIS-1216528 (IIS-1360566)
NSF IIS-0844566 (IIS-1360568)
ONR N000140910099