Pith Number

pith:GGJQXY5R

pith:2026:GGJQXY5RVGEXOFUMIDY55ZTUB6

not attested not anchored not stored refs resolved

Semantic-Fast-SAM: Efficient Semantic Segmenter

Byunghyun Kim

Semantic-Fast-SAM produces accurate semantic segmentation maps in real time by pairing rapid mask generation with category labeling.

arxiv:2604.20169 v2 · 2026-04-22 · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GGJQXY5RVGEXOFUMIDY55ZTUB6}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Experiments on Cityscapes and ADE20K benchmarks demonstrate that SFS matches the accuracy of prior SAM-based methods (mIoU ~ 70.33 on Cityscapes and 48.01 on ADE20K) while achieving approximately 20x faster inference than SSA in the closed-set setting. We also show that SFS effectively handles open-vocabulary segmentation by leveraging CLIP-based semantic heads, outperforming recent open-vocabulary models on broad class labeling.

C2weakest assumption

That the integration of SSA semantic labeling with FastSAM masks preserves mask quality and semantic accuracy without introducing significant errors or requiring extensive retraining, and that CLIP heads generalize reliably to open-vocabulary cases beyond the tested benchmarks.

C3one line summary

Semantic-Fast-SAM matches prior SAM-based semantic segmentation accuracy on Cityscapes and ADE20K while running about 20 times faster by combining FastSAM with SSA labeling and CLIP for open-vocabulary cases.

References

16 extracted · 16 resolved · 3 Pith anchors

[1] Segment Anything 2023 · arXiv:2304.02643

[2] Semantic segment anything 2023

[3] Oneformer: One transformer to rule universal image segmentation 2023

[4] Masked-attention mask transformer for universal image segmentation 2022

[5] Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation 2022

Receipt and verification

First computed	2026-06-30T02:17:21.374364Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

31930be3b1a98977168c40f1dee6740facaf094bad608b30f83a7f07ce235609

Aliases

arxiv: 2604.20169 · arxiv_version: 2604.20169v2 · doi: 10.48550/arxiv.2604.20169 · pith_short_12: GGJQXY5RVGEX · pith_short_16: GGJQXY5RVGEXOFUM · pith_short_8: GGJQXY5R

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/GGJQXY5RVGEXOFUMIDY55ZTUB6 \
  | 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: 31930be3b1a98977168c40f1dee6740facaf094bad608b30f83a7f07ce235609

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fe473840e1ffeeefa799e6e2efd432f530cdc167d2f88f5366676ccf704193d7",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-04-22T04:18:39Z",
    "title_canon_sha256": "3233394f4832db88b49e0ba75d8e9b071260b3ef8aaf18895bf91b7ef667c20e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.20169",
    "kind": "arxiv",
    "version": 2
  }
}