Proposes MMOT, an optimal transport-based online mixture model with dynamic preservation strategy, for improved handling of multimodal data in online incremental learning.
Implementation Detail We implement our proposed method and baselines on the same code base, based on the learner-evaluator framework proposed in [8]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
Proposes MMOT, an optimal transport-based online mixture model with dynamic preservation strategy, for improved handling of multimodal data in online incremental learning.