VJE is a new variational non-contrastive SSL method that models target embeddings with a directional-radial Student-t distribution to enable structured uncertainty estimation directly in the learned representation space.
Ryota Okumura, Tadahiro Taniguchi, Yosinobu Hagiwara, and Akira Taniguchi
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
SSNG replaces sampling-based updates in MHNG with symmetric self-supervised representation alignment using Gumbel-Softmax for discrete messages, yielding higher linear-probe classification accuracy on CIFAR-10 and ImageNet-100 than referential, reconstruction, or MHNG baselines.
citing papers explorer
-
Joint Embedding Variational Bayes
VJE is a new variational non-contrastive SSL method that models target embeddings with a directional-radial Student-t distribution to enable structured uncertainty estimation directly in the learned representation space.
-
SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication
SSNG replaces sampling-based updates in MHNG with symmetric self-supervised representation alignment using Gumbel-Softmax for discrete messages, yielding higher linear-probe classification accuracy on CIFAR-10 and ImageNet-100 than referential, reconstruction, or MHNG baselines.