AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

TF-FAS: Twofold-Element Fine-Grained Semantic Guidance for Generalizable Face Anti-Spoofing

Xudong Wang, Ke-Yue Zhang, Taiping Yao, Qianyu Zhou, Shouhong Ding, Pingyang Dai, Rongrong Ji

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 23 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
add FCEM (fine-grained categorical element module) (ablation)dual-stream CLIP baseline · C->I, C->M, C->O averageHTER: 17.22 -> 9.39Improved
add CEDM (content element decoupling module) (ablation)baseline + FCEM · C->I, C->M, C->O averageHTER: 9.39 -> 6.14Improved
use fine-grained instead of coarse category prompts (ablation)FCEM · C->I, C->M, C->O averageHTER: 17.22 -> 13.87Improved
learn fine-grained prompts with CoOp instead of manual prompts (ablation)FCEM · C->I, C->M, C->O averageHTER: 13.87 -> 14.56Hurt
expand category prompts via GPT-4 augmentation (ablation)FCEM · C->I, C->M, C->O averageHTER: 13.87 -> 11.55Improved
add filtering of augmented samples (ablation)FCEM · C->I, C->M, C->O averageHTER: 11.55 -> 10.82Improved
add adaptive weight learning for prompts (ablation)FCEM · C->I, C->M, C->O averageHTER: 10.82 -> 9.39Improved
use orthogonality disentangling loss instead of CLUB, MINE or contrastive (ablation)CEDM · C->I, C->M, C->O averageHTER: 7.58 (MINE) -> 6.14Improved
disentangle both environment and face semantics instead of one (ablation)CEDM · C->I, C->M, C->O averageHTER: 6.50 (face only) -> 6.14 (all)Mixed
add CelebA-Spoof as extra source dataTF-FAS · Protocol 1 averageHTER: 2.19 -> 1.27Improved

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