Pith. sign in

REVIEW 2 cited by

On Self Modulation for Generative Adversarial Networks

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 1810.01365 v2 pith:KMJYJ5DV submitted 2018-10-02 cs.LG cs.CVstat.ML

On Self Modulation for Generative Adversarial Networks

classification cs.LG cs.CVstat.ML
keywords self-modulationadversarialarchitecturalchangedatagenerativegeneratormodification
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Training Generative Adversarial Networks (GANs) is notoriously challenging. We propose and study an architectural modification, self-modulation, which improves GAN performance across different data sets, architectures, losses, regularizers, and hyperparameter settings. Intuitively, self-modulation allows the intermediate feature maps of a generator to change as a function of the input noise vector. While reminiscent of other conditioning techniques, it requires no labeled data. In a large-scale empirical study we observe a relative decrease of $5\%-35\%$ in FID. Furthermore, all else being equal, adding this modification to the generator leads to improved performance in $124/144$ ($86\%$) of the studied settings. Self-modulation is a simple architectural change that requires no additional parameter tuning, which suggests that it can be applied readily to any GAN.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

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

  1. UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors

    cs.CV 2026-06 unverdicted novelty 6.0

    UniPET proposes a universal PET denoising network with style alignment network (SAN) and region-aware learning strategy (RALS) to handle varied dose reduction factors via domain generalization.

  2. SIGMA: Bridging Structural and Distributional Gaps for Vision Foundation Model Adaptation

    cs.CV 2026-05 unverdicted novelty 5.0

    SIGMA proposes a lightweight PEFT adapter consisting of scale-adaptive fusion and semantic modulation to bridge structural and distributional gaps when adapting vision foundation models to dense tasks.