Pith Number

pith:2UX53KM2

pith:2026:2UX53KM2H73PVEEM4TCZ2W33TW

not attested not anchored not stored refs resolved

Flow Augmentation and Knowledge Distillation for Lightweight Face Presentation Attack Detection

Kejie Huang, Muhammad Shahid Jabbar, Muhammad Sohail Ibrahim, Shujaat Khan, Taha Hasan Masood Siddique

Lightweight RGB-only student learns motion cues via distillation from a flow-augmented teacher, matching detection accuracy without computing optical flow at inference.

arxiv:2605.13108 v1 · 2026-05-13 · 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{2UX53KM2H73PVEEM4TCZ2W33TW}

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

The distilled student achieves performance comparable to or better than the teacher while significantly reducing parameters and FLOPs, achieving 52 FPS on an NVIDIA Jetson Orin Nano, with reported HTER values of 0.0% on Replay-Attack and Replay-Mobile.

C2weakest assumption

That logit distillation from the flow-augmented teacher successfully imbues the RGB-only student with motion-discriminative features sufficient to maintain low error rates across diverse spoofing types and capture conditions without explicit flow at inference.

C3one line summary

A flow-augmented teacher transfers motion-aware knowledge via logit distillation to an RGB-only student model, enabling real-time face presentation attack detection with near-zero error rates on standard benchmarks.

References

31 extracted · 31 resolved · 0 Pith anchors

[1] Deep learning for face anti-spoofing: A survey, 2023

[2] Transfer learning using convolutional neural networks for face anti- spoofing, 2017

[3] A performance evaluation of convolu- tional neural networks for face anti spoofing, 2019

[4] 3d convolutional neural network based on face anti-spoofing, 2017

[5] Learning deep models for face anti-spoofing: Binary or auxiliary supervision, 2018

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:08:58.142887Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d52fdda99a3ff6fa908ce4c59d5b7b9d8b0109d6fea9fe55e07f3af464a15313

Aliases

arxiv: 2605.13108 · arxiv_version: 2605.13108v1 · doi: 10.48550/arxiv.2605.13108 · pith_short_12: 2UX53KM2H73P · pith_short_16: 2UX53KM2H73PVEEM · pith_short_8: 2UX53KM2

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/2UX53KM2H73PVEEM4TCZ2W33TW \
  | 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: d52fdda99a3ff6fa908ce4c59d5b7b9d8b0109d6fea9fe55e07f3af464a15313

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a1c05feb8584ef17886e18da888e9a09467a5c77e3c389d2e708a9adf39fcf35",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T07:19:28Z",
    "title_canon_sha256": "e04a1d01646ff05a14d341a2b4a05a0d37339f1a69e5de3d389a579f6eeaacf0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13108",
    "kind": "arxiv",
    "version": 1
  }
}