Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Jang, Minguk"'
Autor:
Jang, Minguk, Chung, Hye Won
Test-time adaptation (TTA) is an effective approach to mitigate performance degradation of trained models when encountering input distribution shifts at test time. However, existing TTA methods often suffer significant performance drops when facing a
Externí odkaz:
http://arxiv.org/abs/2411.15204
Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's prediction o
Externí odkaz:
http://arxiv.org/abs/2207.10792
Autor:
Jang, Minguk, Chung, Sae-Young
We propose Few-Example Clustering (FEC), a novel algorithm that performs contrastive learning to cluster few examples. Our method is composed of the following three steps: (1) generation of candidate cluster assignments, (2) contrastive learning for
Externí odkaz:
http://arxiv.org/abs/2207.04050