← Search

Xin Jin*

2 accepted papers

2024

Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback

ECCV 2024poster

"Representation disentanglement may help AI fundamentally understand the real world and thus benefit both discrimination and generation tasks. It currently has at least three unresolved core issues: (i) heavy reliance on label annotation and synthetic data — causing poor generalization on natural sc…

Cited by 7SourcePDFScholar
2024

SUMix: Mixup with Semantic and Uncertain Information

ECCV 2024poster

"Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image with patches from another to generate the mixed image. Simi…