pith:XZF5JM37
Smoothing Slot Attention Iterations and Recurrences
SmoothSA improves object-centric learning by smoothing slot attention iterations and recurrences.
arxiv:2508.05417 v5 · 2025-08-07 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{XZF5JM37AXCISRWA2R6Y55B6LB}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We address these issues with our SmoothSA: (1) To smooth SA iterations on image or video's first frame, we preheat cold-start queries with rich input-feature information, by a tiny module self-distilled inside OCL; (2) To smooth SA recurrences across video's first and non-first frames, we differentiate the homogeneous aggregation transforms by using full and single iterations respectively.
The assumption that a self-distilled tiny module can reliably inject useful sample-specific cues into cold-start queries without introducing new biases or requiring extra supervision, and that switching between full and single iterations is sufficient to handle the information difference between first and non-first frames.
SmoothSA improves slot attention by preheating cold-start queries on first frames and applying full iterations there versus single iterations on subsequent video frames.
Receipt and verification
| First computed | 2026-05-28T02:04:42.176377Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
be4bd4b37f05c48946c0d47d8ef43e584d04f13eac4f0899cc4ca4b6857926d0
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/XZF5JM37AXCISRWA2R6Y55B6LB \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: be4bd4b37f05c48946c0d47d8ef43e584d04f13eac4f0899cc4ca4b6857926d0
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "b6b12b3881dd4223a9fc48052d20907da7c1763caab065bc47306abf43b30f08",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2025-08-07T14:09:33Z",
"title_canon_sha256": "09164ef804a9849ed982a8cf3759371e12b02a39750ab6d3f917eab9251f591e"
},
"schema_version": "1.0",
"source": {
"id": "2508.05417",
"kind": "arxiv",
"version": 5
}
}