LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection

• URL: http://arxiv.org/abs/2608.09633v2
• Date: Thu, 13 Aug 2026 12:11:46 GMT
• Title: LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection
• Abstract summary: Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks.<n>While PAD methods achieve strong performance within individual datasets, their performance degrades under cross-dataset evaluation.<n>Foundation models (FMs) have emerged as a promising alternative because typical PAD datasets are small relative to the scale used for web-based pretraining.
• Score: 6.441953169734952
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks. While PAD methods achieve strong performance within individual datasets, their performance degrades under cross-dataset evaluation. Variations in sensors or lighting conditions can reduce the effectiveness of detectors from near-perfect to nearly random. Foundation models (FMs) have emerged as a promising alternative because typical PAD datasets, such as the MCIO benchmarks (MSU-MFSD, CASIA-FASD, Replay-Attack, and OULU-NPU), are small relative to the scale used for web-based pretraining. However, existing PAD systems primarily focus on CLIP-based foundation models, while overlooking other FMs with different architectures and training procedures. This study addresses this question by systematically evaluating 32 FMs. Zero-shot prompting achieves performance near chance across model families and scales. The vision encoders, when low-rankadapted (LoRA) with fewer than 1% trainable weights, achieve below 2% intra-dataset ACER in most cases, while cross-dataset ACER is substantially higher. LoRA primarily refines the decision boundary within a dataset, suggesting that pretrained representations and the adaptation dataset play a larger role in cross-dataset generalization than the evaluated lightweight adaptation strategy.

Related papers

• PCQA-R1: Advancing Generalized 3D Point Cloud Quality Assessment with Reinforcement Learning [51.75061005702151]
  No-reference point cloud quality assessment (PCQA) has been an active topic in recent years and is used to measure and optimize the visual experience of point clouds.<n>We present PCQA-R1, the first reinforcement learning LMM for 3D point cloud quality assessment to simultaneously model quality understanding and scoring.
  arXiv  Detail & Related papers  (2026-08-19T07:21:58Z)
• Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark [32.89408229880636]
  Face presentation attack detection remains challenging under cross-dataset evaluation.<n>Do general-purpose vision foundation models encode PAD-relevant information accessible with minimal task-specific training?<n>We evaluate 24 frozen encoders, including self-supervised vision transformers, vision-language encoders, and supervised CNNs.
  arXiv  Detail & Related papers  (2026-07-29T14:52:25Z)
• RoHOI: Robustness Benchmark for Human-Object Interaction Detection [84.78366452133514]
  Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support.<n>We introduce the first benchmark for HOI detection, evaluating model resilience under diverse challenges.<n>Our benchmark, RoHOI, includes 20 corruption types based on the HICO-DET and V-COCO datasets and a new robustness-focused metric.
  arXiv  Detail & Related papers  (2025-07-12T01:58:04Z)
• FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detection [8.605999078286567]
  Presentation attack detection (PAD) algorithms need to be generalizable to unseen domains.<n>Foundation models (FM) are pre-trained on extensive datasets, achieving remarkable results when generalizing to unseen domains.<n>We release the implementation of FoundPAD at https://github.com/gurayozgur/FoundPAD.
  arXiv  Detail & Related papers  (2025-01-06T10:14:52Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• Class Imbalance in Object Detection: An Experimental Diagnosis and Study of Mitigation Strategies [0.5439020425818999]
  This study introduces a benchmarking framework utilizing the YOLOv5 single-stage detector to address the problem of foreground-foreground class imbalance. We scrutinized three established techniques: sampling, loss weighing, and data augmentation. Our comparative analysis reveals that sampling and loss reweighing methods, while shown to be beneficial in two-stage detector settings, do not translate as effectively in improving YOLOv5's performance.
  arXiv  Detail & Related papers  (2024-03-11T19:06:04Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• A Meta-Learning Approach to Predicting Performance and Data Requirements [163.4412093478316]
  We propose an approach to estimate the number of samples required for a model to reach a target performance. We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset. We introduce a novel piecewise power law (PPL) that handles the two data differently.
  arXiv  Detail & Related papers  (2023-03-02T21:48:22Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Towards Better Object Detection in Scale Variation with Adaptive Feature Selection [3.5352273012717044]
  We propose a novel adaptive feature selection module (AFSM) to automatically learn the way to fuse multi-level representations in the channel dimension. It significantly improves the performance of the detectors that have a feature pyramid structure. A class-aware sampling mechanism (CASM) is proposed to tackle the class imbalance problem.
  arXiv  Detail & Related papers  (2020-12-06T13:41:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.