Cyclically Disentangled Feature Translation for Face Anti-spoofing
- URL: http://arxiv.org/abs/2212.03651v1
- Date: Wed, 7 Dec 2022 14:12:34 GMT
- Title: Cyclically Disentangled Feature Translation for Face Anti-spoofing
- Authors: Haixiao Yue, Keyao Wang, Guosheng Zhang, Haocheng Feng, Junyu Han,
Errui Ding, Jingdong Wang
- Abstract summary: We propose a novel domain adaptation method called cyclically disentangled feature translation network (CDFTN)
CDFTN generates pseudo-labeled samples that possess: 1) source domain-invariant liveness features and 2) target domain-specific content features, which are disentangled through domain adversarial training.
A robust classifier is trained based on the synthetic pseudo-labeled images under the supervision of source domain labels.
- Score: 61.70377630461084
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Current domain adaptation methods for face anti-spoofing leverage labeled
source domain data and unlabeled target domain data to obtain a promising
generalizable decision boundary. However, it is usually difficult for these
methods to achieve a perfect domain-invariant liveness feature disentanglement,
which may degrade the final classification performance by domain differences in
illumination, face category, spoof type, etc. In this work, we tackle
cross-scenario face anti-spoofing by proposing a novel domain adaptation method
called cyclically disentangled feature translation network (CDFTN).
Specifically, CDFTN generates pseudo-labeled samples that possess: 1) source
domain-invariant liveness features and 2) target domain-specific content
features, which are disentangled through domain adversarial training. A robust
classifier is trained based on the synthetic pseudo-labeled images under the
supervision of source domain labels. We further extend CDFTN for multi-target
domain adaptation by leveraging data from more unlabeled target domains.
Extensive experiments on several public datasets demonstrate that our proposed
approach significantly outperforms the state of the art.
Related papers
- Generative Domain Adaptation for Face Anti-Spoofing [38.12738183385737]
Face anti-spoofing approaches based on unsupervised domain adaption (UDA) have drawn growing attention due to promising performances for target scenarios.
Most existing UDA FAS methods typically fit the trained models to the target domain via aligning the distribution of semantic high-level features.
We propose a novel perspective of UDA FAS that directly fits the target data to the models, stylizes the target data to the source-domain style via image translation, and further feeds the stylized data into the well-trained source model for classification.
arXiv Detail & Related papers (2022-07-20T16:24:57Z) - Generalizable Representation Learning for Mixture Domain Face
Anti-Spoofing [53.82826073959756]
Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios.
We propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels.
To overcome the limitation, we propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels.
arXiv Detail & Related papers (2021-05-06T06:04:59Z) - Preserving Semantic Consistency in Unsupervised Domain Adaptation Using
Generative Adversarial Networks [33.84004077585957]
We propose an end-to-end novel semantic consistent generative adversarial network (SCGAN)
This network can achieve source to target domain matching by capturing semantic information at the feature level.
We demonstrate the robustness of our proposed method which exceeds the state-of-the-art performance in unsupervised domain adaptation settings.
arXiv Detail & Related papers (2021-04-28T12:23:30Z) - Instance Level Affinity-Based Transfer for Unsupervised Domain
Adaptation [74.71931918541748]
We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA.
We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process.
We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
arXiv Detail & Related papers (2021-04-03T01:33:14Z) - Disentanglement-based Cross-Domain Feature Augmentation for Effective
Unsupervised Domain Adaptive Person Re-identification [87.72851934197936]
Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching.
One challenge is how to generate target domain samples with reliable labels for training.
We propose a Disentanglement-based Cross-Domain Feature Augmentation strategy.
arXiv Detail & Related papers (2021-03-25T15:28:41Z) - Effective Label Propagation for Discriminative Semi-Supervised Domain
Adaptation [76.41664929948607]
Semi-supervised domain adaptation (SSDA) methods have demonstrated great potential in large-scale image classification tasks.
We present a novel and effective method to tackle this problem by using effective inter-domain and intra-domain semantic information propagation.
Our source code and pre-trained models will be released soon.
arXiv Detail & Related papers (2020-12-04T14:28:19Z) - Unsupervised Cross-domain Image Classification by Distance Metric Guided
Feature Alignment [11.74643883335152]
Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a target domain.
We propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains.
Our model integrates class distribution alignment to transfer semantic knowledge from a source domain to a target domain.
arXiv Detail & Related papers (2020-08-19T13:36:57Z) - Bi-Directional Generation for Unsupervised Domain Adaptation [61.73001005378002]
Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information.
Conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure.
We propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
arXiv Detail & Related papers (2020-02-12T09:45:39Z) - Unsupervised Domain Adaptive Object Detection using Forward-Backward
Cyclic Adaptation [13.163271874039191]
We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training.
Recent adversarial training based domain adaptation methods have shown their effectiveness on minimizing domain discrepancy via marginal feature distributions alignment.
We propose Forward-Backward Cyclic Adaptation, which iteratively computes adaptation from source to target via backward hopping and from target to source via forward passing.
arXiv Detail & Related papers (2020-02-03T06:24:58Z)
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.