AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition

Chien-Yi Wang, Yu-Ding Lu, Shang-Ta Yang, Shang-Hong Lai

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 165 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
reformulate binary face anti-spoofing as fine-grained patch-type recognition using raw-frame patch crops (ablation)PatchNet · OULU-NPU protocol 1ACER (%): 6.25 -> 1.88Improved
use patch crops instead of resized input for binary classification (ablation)PatchNet · OULU-NPU protocol 1ACER (%): 6.25 -> 3.54Improved
use fine-grained classes instead of binary classes with resized input (ablation)PatchNet · OULU-NPU protocol 1ACER (%): 6.25 -> 5.63Improved
add self-supervised similarity loss (ablation)PatchNet with fine-grained patch recognition · OULU-NPU protocol 1ACER (%): 1.88 -> 1.46Improved
add asymmetric margin classification loss (ablation)PatchNet with fine-grained patch recognition · OULU-NPU protocol 1ACER (%): 1.88 -> 0.63Improved
add both asymmetric margin classification and self-supervised similarity losses (ablation)PatchNet · OULU-NPU protocol 1ACER (%): 1.88 -> 0.0Improved
remove angular margin (ablation)PatchNet · O&C&I to MHTER (%): 7.10 -> 10.0Hurt
remove self-supervised similarity loss (ablation)PatchNet · O&C&I to MHTER (%): 7.10 -> 8.9Hurt
replace fine-grained patch classes with coarse classes (ablation)PatchNet · O&C&I to MHTER (%): 7.10 -> 10.24Hurt
use PatchNet rather than the strongest listed baselineface anti-spoofing · OULU-NPU protocol 1ACER (%): 0.2 -> 0.0Improved
use PatchNet rather than the strongest listed baselineface anti-spoofing · SiW protocol 3ACER (%): 1.52±0.13 -> 2.45±0.45Hurt
use PatchNet rather than DC-CDNcross-dataset face anti-spoofing · CASIA-MFSD to Replay-AttackHTER (%): 6.0 -> 9.9Hurt

Later papers that compared with this method

2 later accepted papers report PatchNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy