1 citations · 2 across the 6 of their papers we have counts for
6 papers
Scene-Driven Exploration and GUI Modeling for Android Apps
Xiangyu Zhang, Lingling Fan, Sen Chen +2
Due to the competitive environment, mobile apps are usually produced under pressure with lots of complicated functionality and UI pages. Therefore, it is challenging for various ro…
On-the-fly Improving Performance of Deep Code Models via Input Denoising
Zhao Tian, Junjie Chen, Xiangyu Zhang
Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets. While these deep code models have ac…
Self-supervised Learning by View Synthesis
Shaoteng Liu, Xiangyu Zhang, Tao Hu +1
We present view-synthesis autoencoders (VSA) in this paper, which is a self-supervised learning framework designed for vision transformers. Different from traditional 2D pretrainin…
End-to-End Lyrics Recognition with Self-supervised Learning
Xiangyu Zhang, Shuyue Stella Li, Zhanhong He +2
Lyrics recognition is an important task in music processing. Despite traditional algorithms such as the hybrid HMM- TDNN model achieving good performance, studies on applying end-t…
Understanding Masked Image Modeling via Learning Occlusion Invariant Feature
Xiangwen Kong, Xiangyu Zhang
Recently, Masked Image Modeling (MIM) achieves great success in self-supervised visual recognition. However, as a reconstruction-based framework, it is still an open question to un…
Revisiting the Critical Factors of Augmentation-Invariant Representation Learning
Junqiang Huang, Xiangwen Kong, Xiangyu Zhang
We focus on better understanding the critical factors of augmentation-invariant representation learning. We revisit MoCo v2 and BYOL and try to prove the authenticity of the follow…