Search Results for author:
Found 2 papers, 2 papers with code
Unsupervised Visual Representation Learning via Mutual Information Regularized Assignment
This paper proposes Mutual Information Regularized Assignment (MIRA), a pseudo-labeling algorithm for unsupervised representation learning inspired by information maximization.
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
We propose unsupervised embedding adaptation for the downstream few-shot classification task.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
