Jiaxi Sun — accepted AI-conference papers

2023

Domain Decorrelation with Potential Energy Ranking

Sen Pei, Jiaxi Sun, Richard Yi Da Xu, Shiming Xiang, Gaofeng Meng

AAAI 2023technical

Machine learning systems, especially the methods based on deep learning, enjoy great success in modern computer vision tasks under ideal experimental settings. Generally, these classic deep learning methods are built on the i.i.d. assumption, supposing the training and test data are drawn from the s…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2023

Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation

Rongtao Xu, Changwei Wang, Jiaxi Sun, Shibiao Xu, Weiliang Meng, Xiaopeng Zhang

AAAI 2023technical

Efficiently training accurate deep models for weakly supervised semantic segmentation (WSSS) with image-level labels is challenging and important. Recently, end-to-end WSSS methods have become the focus of research due to their high training efficiency. However, current methods suffer from insuffici…

Cited by 59 Source ↗PDF ↗code ↗Scholar ↗