An online Mahalanobis-distance novelty filter, updated with streaming data, selects a smaller traffic-sign training set that can outperform the full dataset and random sampling.
Densely connected normalizing flows
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Normalizing flows are bijective mappings between inputs and latent representations with a fully factorized distribution. They are very attractive due to exact likelihood valuation and efficient sampling. However, their effective capacity is often insufficient since the bijectivity constraint limits the model width. We address this issue by incrementally padding intermediate representations with noise. We precondition the noise in accordance with previous invertible units, which we describe as cross-unit coupling. Our invertible glow-like modules increase the model expressivity by fusing a densely connected block with Nystrom self-attention. We refer to our architecture as DenseFlow since both cross-unit and intra-module couplings rely on dense connectivity. Experiments show significant improvements due to the proposed contributions and reveal state-of-the-art density estimation under moderate computing budgets.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording
An online Mahalanobis-distance novelty filter, updated with streaming data, selects a smaller traffic-sign training set that can outperform the full dataset and random sampling.