AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

FLIP: Cross-domain Face Anti-spoofing with Language Guidance

Koushik Srivatsan, Muzammal Naseer, Karthik Nandakumar

ICCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Feature calibration for unseen-class detection · 91 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
initialize ViT with CLIP weights instead of ImageNet weights (ablation)ViT for face anti-spoofing · Protocol 1 (zero-shot)average HTER: 6.00 -> 3.48Improved
initialize ViT with ImageNet instead of training from scratch (ablation)ViT for face anti-spoofing · Protocol 1 (zero-shot)average HTER: 25.86 -> 6.00Improved
initialize with BeIT instead of ImageNet (ablation)ViT for face anti-spoofing · Protocol 1 (zero-shot)average HTER: 6.00 -> 8.70Hurt
align image features to text prompts (FLIP-IT) over plain finetuning (FLIP-V) (ablation)FLIP · Protocol 1 (zero-shot)average HTER: 3.48 -> 3.06Improved
align image features to text prompts (FLIP-IT) over plain finetuning (FLIP-V) (ablation)FLIP · Protocol 2 (zero-shot)average HTER: 9.83 -> 10.2Hurt
add multimodal contrastive learning (FLIP-MCL) over FLIP-IT (ablation)FLIP · Protocol 3 (zero-shot)average HTER: 6.03 -> 4.84Improved
use ensemble of prompts instead of a single prompt (ablation)FLIP-IT · Protocol 1 (zero-shot)average HTER: 3.06 vs single prompts 2.94 to 4.52Mixed
remove SimCLR loss or MSE loss from joint loss (ablation)FLIP-MCL · Protocol 1 (zero-shot)average HTER: 3.47 -> 3.01Improved
upweight self-supervised losses to (1,5,5) (ablation)FLIP-MCL · Protocol 1 (zero-shot)average HTER: 3.01 -> 3.67Hurt
full finetuning of CLIP-pretrained ViT image encoderFLIP-V · Protocol 1 (zero-shot)average HTER: 6.00 -> 3.48Improved
FLIP versus zero-shot ViT on target domain MFLIP-MCL · Protocol 1 OCI->MHTER: 1.58 -> 4.95Hurt

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