Yao Xiao

A first-year CS Ph.D. student @ UIUC

Email: ava_xiao@icloud.com

About Me

I am a first-year Ph.D. in Computer Science at the University of Illinois at Urbana-Champaign, supervised by Prof. Derek Hoiem.

I obtained my master's degree from the University of Southern California, advised by Prof. Laurent Itti and Prof. Ram Nevatia. Before that, I got my B.S. degree from Fudan University.

My research interests mainly lie in computer vision, especially in:

• Video understanding: Empowering models with the capability to process unlimited-length videos efficiently.

• Explainable AI: Unveiling model perceptions of the world to enable a transparent latent space.

• Robustness: Improving models' resilience against image distortions and adversarial examples.

Selected Publications (* Equal Contribution)

WACV 2023

PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch

Ke Xu*, Yao Xiao*, Zhaoheng Zheng, Kaijie Cai, Ram Nevatia.

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023.

[Abstract] [Paper] [Bibtex]

We propose PatchZero, a task-agnostic defense that is compatible with multiple downstream models. Specifically, our defense detects the adversarial pixels and “zeros out” the patch region by repainting with mean pixel values. We formulate the patch detection problem as a semantic segmentation task such that our model can generalize to patches of any size and shape. We further design a two-stage adversarial training scheme to defend against the stronger adaptive attacks. Our method achieves state-of-the-art robust ac-curacy without any degrade in the benign performance.

@article{xu2022patchzero, title={PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch}, author={Xu, Ke and Xiao, Yao and Zheng, Zhaoheng and Cai, Kaijie and Nevatia, Ram}, journal={arXiv preprint arXiv:2207.01795}, year={2022} }

ECCV 2022

Contributions of Shape, Texture, and Color in Visual Recognition

Yunhao Ge*, Yao Xiao*, Zhi Xu, Xingrui Wang, Laurent Itti.

European Conference on Computer Vision (ECCV), 2022.

[Abstract] [Paper] [Code] [Bibtex]

We investigate the contributions of three important features of the human visual system (HVS) — shape, texture, and color — to object classification. We build a humanoid vision engine (HVE) that explicitly and separately computes shape, texture, and color features from images. We show that HVE can summarize and rank-order the contributions of the three features to object recognition. With the help of HVE, given any environment (dataset), we can summarize the most important features for the whole task and for each class.

@inproceedings{ge2022contributions, title={Contributions of Shape, Texture, and Color in Visual Recognition}, author={Ge, Yunhao and Xiao, Yao and Xu, Zhi and Wang, Xingrui and Itti, Laurent}, booktitle={European Conference on Computer Vision}, pages={369--386}, year={2022}, organization={Springer} }

CVPR 2021

A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts

Yunhao Ge, Yao Xiao, Zhi Xu, Meng Zheng, Srikrishna Karanam, Terrence Chen, Laurent Itti and Ziyan Wu.

IEEE/ CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[Abstract] [Paper] [Code] [Website] [Video] [Poster] [Bibtex]

We propose a framework (VRX) to interpret classification NNs with intuitive structural visual concepts. Given a trained classification model, the proposed VRX extracts relevant class-specific visual concepts and organizes them using structural concept graphs (SCG) based on pairwise concept relationships. By means of knowledge distillation, we show VRX can take a step towards mimicking the reasoning process of NNs and provide logical, concept-level explanations for final model decisions.

@inproceedings{ge2021peek, title={A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts}, author={Ge, Yunhao and Xiao, Yao and Xu, Zhi and Zheng, Meng and Karanam, Srikrishna and Chen, Terrence and Itti, Laurent and Wu, Ziyan}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={2195--2204}, year={2021} }

→ Full list

Research Experience

AWS AI Rekognition, Amazon, Seattle, WA
Applied Scientist Intern. May 2023 – August 2023
Mentors: Bing Shuai, Xunyu Lin, N Dinesh Reddy; Manager:Davide Modolo

Computer Vision Group, UIUC, Champaign, IL
Research Assistant. August 2022 – Present
Advisor: Prof. Derek Hoiem

IRIS Computer Vision Lab, USC, Los Angeles, CA
Research Assistant. May 2021 – May 2022
Advisor: Prof. Ram Nevatia

iLab, USC, Los Angeles, CA
Research Assistant. August 2020 – December 2021
Advisor: Prof. Laurent Itti

Blog

A place to record my feelings, exploration, and growth. I intend to be casual here, so I decided to use Mandarin for some posts.

• [12/05/2022] 写于博士第一学期结束之际

Some thoughts on the end of the first semester of PhD life.

• [07/12/2022] PhD Guideline

Some guidance from Prof. Derek Hoiem.

→ Full list

Academic Service

Reviewer

• Conference: CVPR (2023, 2022), ICLR 2023, WACV 2023, ECCV 2022, TCV@CVPR 2022, AIBSD@AAAI 2022.

• Journal: IEEE Access.