AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing

Kaicheng Li, Hongyu Yang, Binghui Chen, Pengyu Li, Biao Wang, Di Huang

AAAI 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modal object re-identification · 6 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 RGB-D polysemantic spoof trace disentanglement with cross-modal feature fusionFace anti-spoofing · WMCA GrandTestACER: 0.52 -> 0.27Improved
use RGB-D polysemantic spoof trace disentanglement with cross-modal feature fusionFace anti-spoofing · WMCA LOOMean ACER (%): 7.1±9.9 -> 4.8±6.6Improved
use RGB-D polysemantic spoof trace disentanglement with cross-modal feature fusionFace anti-spoofing · CeFA LOO Protocol 1ACER (%): 6.8±3.5 -> 5.0±1.9Improved
use RGB-D polysemantic spoof trace disentanglement with cross-modal feature fusionFace anti-spoofing · CeFA LOO Protocol 2ACER (%): 1.2±0.6 -> 0.9±0.2Improved
use RGB-D polysemantic spoof trace disentanglement with cross-modal feature fusionFace anti-spoofing · CeFA LOO Protocol 4ACER (%): 9.7±6.1 -> 6.2±1.0Improved
add spoof-trace disentanglement to the original RGB-D classifier (ablation)Face anti-spoofing · WMCA GrandTestACER: 9.0 -> 5.7Improved
add the depth modality alongside the RGB modality (ablation)RGB Only disentanglement · WMCA GrandTestACER: 5.7 -> 0.27Improved
add the RGB modality alongside the depth modality (ablation)DEP Only disentanglement · WMCA GrandTestACER: 3.8 -> 0.27Improved
replace vanilla feature concatenation with the proposed cross-modal fusion module (ablation)RGB-D disentanglement · WMCA GrandTestACER: 1.1 -> 0.27Improved
replace original SA-Gate with the proposed cross-modal fusion module (ablation)RGB-D disentanglement · WMCA GrandTestACER: 0.52 -> 0.27Improved
add center loss (ablation)RGB-D spoof trace disentanglement · WMCA LOOMean ACER (%): 12.4±13.6 -> 4.8±6.6Improved
add identity consistency loss (ablation)RGB-D spoof trace disentanglement · WMCA LOOMean ACER (%): 7.9±9.3 -> 4.8±6.6Improved

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