mlsanityData to 7 Oct 2026

Face Presentation Attack Detection via Content-Adaptive Spatial Operators

arXiv 2602.18965 ↗First posted 21 Feb 2026cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Face presentation attack detection (FacePAD) is critical for securing facial authentication against print, replay, and mask-based spoofing. This paper proposes CASO-PAD, an RGB-only, single-frame model that enhances MobileNetV3 with content-adaptive spatial operators (involution) to better capture localized spoof cues. Unlike spatially shared convolution kernels, the proposed operator generates location-specific, channel-shared kernels conditioned on the input, improving spatial selectivity with minimal overhead. CASO-PAD remains lightweight (3.6M parameters; 0.64 GFLOPs at 256×256) and is trained end-to-end using a standard binary cross-entropy objective. Extensive experiments on Replay-Attack, Replay-Mobile, ROSE-Youtu, and OULU-NPU demonstrate strong performance, achieving 100/100/98.9/99.7% test accuracy, AUC of 1.00/1.00/0.9995/0.9999, and HTER of 0.00/0.00/0.82/0.44%, respectively. On the large-scale SiW-Mv2 Protocol-1 benchmark, CASO-PAD further attains 95.45% accuracy with 3.11% HTER and 3.13% EER, indicating improved robustness under diverse real-world attacks. Ablation studies show that placing the adaptive operator near the network head and using moderate group sharing yields the best accuracy--efficiency balance. Overall, CASO-PAD provides a practical pathway for robust, on-device FacePAD with mobile-class compute and without auxiliary sensors or temporal stacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 82 references that are in the map. First posted on arXiv 21 Feb 2026.

Builds on

19 of 82 references.

References · 19

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  8. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  9. 2019GhostNet: More Features from Cheap Operationscited by 410
  10. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  11. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  12. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
7 more
  1. 2015face anti-spoofing based on color texture analysiscited by 82
  2. 2022Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofingcited by 73
  3. 2021Deep Learning for Face Anti-Spoofing: A Surveycited by 64
  4. 2022Multi-domain Learning for Updating Face Anti-spoofing Modelscited by 39
  5. 2021Unified Detection of Digital and Physical Face Attackscited by 31
  6. 2023Surveillance Face Anti-spoofingcited by 12
  7. 2024Confidence Aware Learning for Reliable Face Anti-spoofingcited by 5

Built on by

Not cited yet.