Tiange Xiang   
向天戈
I am a first-year Ph.D. student in Stanford Vision and Learning Lab (SVL) at the Stanford University. I'm currently rotating with Prof. Fei-Fei Li and Prof. Jiajun Wu.
I received my Bachelor's degree from The University of Sydney, where I was fortunate to work with Prof. Weidong Cai. I was awarded Honors Class I and The University Medal.
I have particular research interests on Machine Learning & Computer Vision.
Contact: {X @ Y}, where X=xtiange, Y=stanford.edu
Google Scholar  / 
Github  / 
Linkedin
|
|
Publications ( * indicates equal contributions)
|
|
In-painting Radiography Images for Unsupervised Anomaly Detection
Tiange Xiang,
Yixiao Zhang,
Yongyi Lu,
Alan L. Yuille,
Chaoyi Zhang,
Weidong Cai,
and Zongwei Zhou
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
We re-formulated unsupervised anomaly detection for radiography images as semantic-sapce in-painting.
[
paper  / 
code
]
|
|
Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
Zijiao Chen*,
Jiaxin Qing*,
Tiange Xiang,
Wan Lin Yue,
and Juan Helen Zhou
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
We decoded photo-realistic visual stimuli from fMRI brain signals.
[
project page  / 
code  / 
paper
]
|
|
DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models
Tiange Xiang,
Mahmut Yurt,
Ali B Syed,
Kawin Setsompop, and
Akshay Chaudhari
International Conference on Learning Representations (ICLR), 2023
We achieved self-supervised MRI denoising through generative diffusion models.
[
paper  / 
code
]
|
|
Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
Tiange Xiang,
Chaoyi Zhang,
Yang Song,
Jianhui Yu, and
Weidong Cai
IEEE/CVF International Conference on Computer Vision (ICCV), 2021
We proposed a geometry-aware feature aggregation operator for point cloud analysis. SOTA performances on multiple fundamental benchmarks.
[
project page  / 
paper  / 
code
]
|
|
Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond
Tiange Xiang,
Chaoyi Zhang,
Xinyi Wang,
Yang Song,
Dongnan Liu,
Heng Huang,
and Weidong Cai
Medical Image Analysis, 2022
A very efficient and light-weight encoder-decoder network that achieved SOTA performances on multiple 2D and 3D medical image segmentation benchmarks.
[
project page  / 
paper
]
|
|
BiX-NAS: Searching Efficient Bi-directional Architectures for Medical Image Segmentation
Xinyi Wang*,
Tiange Xiang*,
Chaoyi Zhang,
Yang Song,
Dongnan Liu,
Heng Huang,
and Weidong Cai
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021
We proposed a two-phase NAS method to search a super efficient bi-directional architecture for medical image segmentation.
[
project page  / 
paper  / 
code
]
|
|
BiO-Net: Learning Recurrent Bidirectional Connections for Encoder-Decoder Architecture
Tiange Xiang,
Chaoyi Zhang,
Dongnan Liu,
Yang Song,
Heng Huang,
and Weidong Cai
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2020
We proposed bi-directional skip connections in the encoder-decoder architecture. Better performances can be achived without increasing network parameter.
[
project page  / 
paper  / 
code
]
|
|
DSNet: A Weakly-Supervised Dual-Stream Framework for Effective Gigapixel Pathology Image Analysis
Tiange Xiang,
Yang Song,
Chaoyi Zhang,
Dongnan Liu,
Mei Chen,
Fan Zhang,
Heng Huang,
Lauren O'Donnell,
and Weidong Cai
IEEE Transactions on Medical Imaging, 2022
We proposed an attention-based network to combine global-local visual clues for weakly-supervised WSI analysis.
[
paper
]
|
|
Partial Graph Reasoning for Neural Network Regularization
Tiange Xiang,
Chaoyi Zhang,
Yang Song,
Siqi Liu,
Hongliang Yuan, and
Weidong Cai
We formulated network regularization as generative distortions through learnable graph reasoning modules.
[
project page  / 
paper
]
|
|
Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool
Tiange Xiang,
Hongliang Yuan,
Haozhi Huang, and
Yujin Shi
We achieved real-time denoising for online rendering at adaptive spp counts. Multiple novel operators were designed in our two-phase denoising framework.
[
paper
]
|
Conference reviewer for CVPR(2021,2022,2023), MICCAI(2021, 2022, 2023), ICCV 2023, ICML 2022, ECCV 2022, NeurIPS 2022.
Journal reviewer for IEEE TPAMI, IEEE TMI, Neurocomputing.
|