Rui Zhu

Rui Zhu

Auto-generated profile, based on publicly available information

Rui Zhu

ByteDance Seed

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 July 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
RZRui Zhu
Rui Zhu
YBYalong Bai
Yalong Bai
TYTing Yao
Ting Yao
JLJingen Liu
Jingen Liu
ZSZhenglong Sun
Zhenglong Sun
CCChang Wen Chen
Chang Wen Chen
Masked autoencoder (MAE) has been regarded as a capable self-supervised learner for various downstream tasks. Nevertheless, the model still lacks high-level discriminability, which results in poor linear probing performance. In view of the fact that strong augmentation plays an essential role in contrastive learning, can we capitalize on strong augmentation in MAE? The difficulty originates from the pixel uncertainty caused by strong augmentation that may affect the reconstruction, and thus, directly introducing strong augmentation into MAE often hurts the performance. In this article, we delve into the potential of strong augmented views to enhance MAE while maintaining MAE’s advantages. To this end, we propose a simple yet effective masked Siamese autoencoder (MSA) model, which consists of a student branch and a teacher branch. The student branch derives MAE’s advanced architecture, and the teacher branch treats the unmasked strong view as an exemplary teacher to impose high-level discrimination onto the student branch. We demonstrate that our MSA can improve the model’s spatial perception capability and, therefore, globally favors interimage discrimination. Empirical evidence shows that the model pretrained by MSA provides superior performances across different downstream tasks. Notably, linear probing performance on frozen features extracted from MSA leads to 6.1% gains over MAE on ImageNet-1k. Fine-tuning (FT) the network on VQAv2 task finally achieves 67.4% accuracy, outperforming 1.6% of the supervised method DeiT and 1.2% of MAE. Codes and models are available at https://github.com/KimSoybean/MSA.

10 September 2026
Verified
Book Chapter
Closed access
PDF file
QZQinyu Zhao
Qinyu Zhao
GZGuangting Zheng
Guangting Zheng
TYTao Yang
Tao Yang
RZRui Zhu
Rui Zhu
XLXingjian Leng
Xingjian Leng
LZLiang Zheng
Liang Zheng