AI Paper Atlas

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

Feature Generation and Hypothesis Verification for Reliable Face Anti-spoofing

Shice Liu, Shitao Lu, Hongyi Xu, Jing Yang, Shouhong Ding, Lizhuang Ma

AAAI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 46 citations (OpenAlex)

Read the paperCheck 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
Use FGHV rather than the strongest listed baselinecross-dataset face anti-spoofing · O&C&I to MHTER (%): 10.83 -> 9.17Improved
Use FGHV rather than the strongest listed baselinecross-dataset face anti-spoofing · O&M&I to CHTER (%): 15.21 -> 12.47Improved
Use FGHV rather than the strongest listed baselinecross-dataset face anti-spoofing · O&C&M to IHTER (%): 11.63 -> 16.29Hurt
Use FGHV rather than the strongest listed baselinecross-dataset face anti-spoofing · I&C&M to OHTER (%): 13.16 -> 13.58Hurt
Use both real-face and known-attack feature generators with all three constraints (ablation)FGHV · O&C&I to MHTER (%): 25.00 -> 9.17Improved
Add the real-face feature generator (ablation)FGHV with only known-attack FGN · O&C&I to MHTER (%): 20.00 -> 9.17Improved
Add the known-attack feature generator (ablation)FGHV with only real-face FGN · O&C&I to MHTER (%): 15.83 -> 9.17Improved
Add VAR to RCC (ablation)FGHV · O&C&I to MHTER (%): 14.16 -> 10.00Improved
Add DDC to RCC (ablation)FGHV · O&C&I to MHTER (%): 14.16 -> 10.83Improved
Add RCC to VAR+DDC (ablation)FGHV · O&C&I to MHTER (%): 12.50 -> 9.17Improved
Use VAR alone instead of RCC (ablation)FGHV · O&C&I to MHTER (%): 14.16 -> 33.33Hurt
Increase the number of sampled latent vectors (ablation)FGHV · I&C&M to OAUCImproved

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