Pith. sign in

REVIEW 1 cited by

Densely connected normalizing flows

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.04627 v3 pith:QKJ4RH75 submitted 2021-06-08 cs.LG cs.AIcs.CV

classification cs.LGcs.AIcs.CV
keywords connectedcross-unitdenselyflowsinvertiblemodelnoisenormalizing
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording

    cs.CV 2025-07 conditional novelty 4.0 of 10

    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.

Pith tools