← Search

Zimeng Luo

2 accepted papers

2023

Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning

CVPR 2023poster

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small models. In this study, we propose a Multi-mode Online Knowledge Distillation method (…

Cited by 38SourcePDFScholar
2023

Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning

ICCV 2023poster

In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented "views" of the same image closer while pushing all other images further apart, which has been proven to be effective. However, it is unavoidable to construct undesirable view…

Cited by 7PDFcodeScholar