Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Yang You

Yang You

Active-Learning-as-a-Service: An Efficient MLOps System for Data-Centric AI

Jul 19, 2022
Yizheng Huang, Huaizheng Zhang, Yuanming Li, Chiew Tong Lau, Yang You

Figure 1 for Active-Learning-as-a-Service: An Efficient MLOps System for Data-Centric AI

Figure 2 for Active-Learning-as-a-Service: An Efficient MLOps System for Data-Centric AI

Figure 3 for Active-Learning-as-a-Service: An Efficient MLOps System for Data-Centric AI

Figure 4 for Active-Learning-as-a-Service: An Efficient MLOps System for Data-Centric AI

* 8 pages, 7 figures

Access Paper or Ask Questions

Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

May 28, 2022
Jianfei Yang, Xiangyu Peng, Kai Wang, Zheng Zhu, Jiashi Feng, Lihua Xie, Yang You

Figure 1 for Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

Figure 2 for Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

Figure 3 for Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

Figure 4 for Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

* A black-box model adaptation approach that proposes divide-to-adapt to suppress the confirmation bias

Access Paper or Ask Questions

FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders

May 23, 2022
Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Jiankang Deng, Xinchao Wang, Hakan Bilen, Yang You

Figure 1 for FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders

Figure 2 for FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders

Figure 3 for FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders

Figure 4 for FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders

* A new paradigm for privacy-preserving face recognition via MAE

Access Paper or Ask Questions

Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Apr 30, 2022
Kai Wang, Xiangyu Peng, Shuo Yang, Jianfei Yang, Zheng Zhu, Xinchao Wang, Yang You

Figure 1 for Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Figure 2 for Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Figure 3 for Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Figure 4 for Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

* LC-Booster is an efficient method for LNL problems

Access Paper or Ask Questions

Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation

Apr 06, 2022
Wangbo Zhao, Kai Wang, Xiangxiang Chu, Fuzhao Xue, Xinchao Wang, Yang You

Figure 1 for Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation

Figure 2 for Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation

Figure 3 for Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation

Figure 4 for Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation

* Accepted to CVPR2022

Access Paper or Ask Questions

CAFE: Learning to Condense Dataset by Aligning Features

Mar 27, 2022
Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Shuo Yang, Shuo Wang, Guan Huang, Hakan Bilen, Xinchao Wang, Yang You

Figure 1 for CAFE: Learning to Condense Dataset by Aligning Features

Figure 2 for CAFE: Learning to Condense Dataset by Aligning Features

Figure 3 for CAFE: Learning to Condense Dataset by Aligning Features

Figure 4 for CAFE: Learning to Condense Dataset by Aligning Features

* The manuscript has been accepted by CVPR-2022!

Access Paper or Ask Questions