arXiv:2212.13420
Self Meta Pseudo Labels: Meta Pseudo Labels Without The Teacher
원문 초록
We present Self Meta Pseudo Labels, a novel semi-supervised learning method similar to Meta Pseudo Labels but without the teacher model. We introduce a novel way to use a single model for both generating pseudo labels and classification, allowing us to store only one model in memory instead of two. Our method attains similar performance to the Meta Pseudo Labels method while drastically reducing memory usage.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ViTSGMM: A Robust Semi-Supervised Image Recognition Network Using Sparse Labels
Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\mathbf{\texttt{D}}$ual-$\mathbf{\texttt{H}}$ead $\mathbf{\texttt{O}}$ptimization
SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification
Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
Meta Co-Training: Two Views are Better than One
토론
이 논문과 연결된 포럼 글이 아직 없습니다.