pith:YNPXEG5Q
BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning
Burst spikes and dual-channel attention improve accuracy in spiking vision transformers without sacrificing energy efficiency.
arxiv:2604.23165 v2 · 2026-04-25 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{YNPXEG5Q42IYA7EJWZQ5G3AHYW}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Extensive experiments on both static and event-based vision benchmarks demonstrate that BSViT consistently outperforms existing spiking Transformers in accuracy while maintaining competitive energy efficiency.
That encoding queries with binary spikes, keys with burst spikes, and values with dual excitatory/inhibitory binary channels will increase representational capacity and spike interactions while preserving addition-only computation and hardware compatibility.
BSViT introduces burst spike coding and dual-channel burst spiking self-attention in a Vision Transformer, outperforming prior spiking transformers on static and event-based vision tasks with competitive energy efficiency.
Receipt and verification
| First computed | 2026-06-12T01:08:25.104658Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
c35f721bb0e691807c89b661d36c07c599cc5c503b334f56d34c1fbad728475b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/YNPXEG5Q42IYA7EJWZQ5G3AHYW \
| 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: c35f721bb0e691807c89b661d36c07c599cc5c503b334f56d34c1fbad728475b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "2a6ef00bd0c79f55bcf79de1c6c0f8a429dcbe870fe407398ac11a1f117a3b0e",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-25T06:33:04Z",
"title_canon_sha256": "4c4310311245a3712017f79ff07013c6a64cd891d2fc50e3031b47847568c095"
},
"schema_version": "1.0",
"source": {
"id": "2604.23165",
"kind": "arxiv",
"version": 2
}
}