Reducing Deep Network Complexity via Sparse Hierarchical Fourier Interaction Networks

Andrew Kiruluta; Samantha Williams

Reducing Deep Network Complexity via Sparse Hierarchical Fourier Interaction Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1801.01451 v3 pith:BFF4UAWW submitted 2017-12-15 cs.CV cs.LG

Andrew Kiruluta , Samantha Williams This is my paper · ORCID

classification cs.CVcs.LG

keywords fourierhierarchicalinteractionnetworkssparseaccessaffordsarchitectural

verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments

read the original abstract

This paper presents a Sparse Hierarchical Fourier Interaction Networks, an architectural building block that unifies three complementary principles of frequency domain modeling: A hierarchical patch wise Fourier transform that affords simultaneous access to local detail and global context; A learnable, differentiable top K masking mechanism which retains only the most informative spectral coefficients, thereby exploiting the natural compressibility of visual and linguistic signals.

Discussion (0). Continue with ORCID 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

From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMs
cs.CV 2025-06 reject novelty 4.0 of 10

A spectral-dictionary VLM claims to match mid-scale baselines without convolutions or self-attention, but its O(L log L) complexity argument is not supported by the equations as written.

Pith tools