Papers › Rethinking FUN: Frequency-Domain Utilization Networks

Rethinking FUN: Frequency-Domain Utilization Networks

6 Dec 2020arXiv:2012.03357archive 2025-07-28

Kfir Goldberg, Stav Shapiro, Elad Richardson, Shai Avidan

The search for efficient neural network architectures has gained much focus in recent years, where modern architectures focus not only on accuracy but also on inference time and model size. Here, we present FUN, a family of novel Frequency-domain Utilization Networks. These networks utilize the inherent efficiency of the frequency-domain by working directly in that domain, represented with the Discrete Cosine Transform. Using modern techniques and building blocks such as compound-scaling and inverted-residual layers we generate a set of such networks allowing one to balance between size, latency and accuracy while outperforming competing RGB-based models. Extensive evaluations verifies that our networks present strong alternatives to previous approaches. Moreover, we show that working in frequency domain allows for dynamic compression of the input at inference time without any explicit change to the architecture.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

kfir99/FUN officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Efficient Neural Network

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Discrete Cosine Transform

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections