Proceedings ArticleDOI
A-DeepPixBis: Attentional Angular Margin for Face Anti-Spoofing
Md. Sourave Hossain,Labiba Rupty,Koushik Roy,Hasan M,Shirshajit Sengupta,Nabeel Mohammed +5 more
- pp 1-8
Reads0
Chats0
TLDR
This study proposes a variant of BCE that enforces a margin in angular space and incorporate it in training the DeepPixBis model and presents a method to incorporate such a loss for attentive pixel wise supervision applicable in a fully convolutional setting.Abstract:
Face Anti Spoofing (FAS) systems are used to identify malicious spoofing attempts targeting face recognition systems using mediums such as video replay or printed papers. With increasing adoption of face recognition technology as a biometric authentication method, FAS techniques are gaining in importance. From a learning perspective, such systems pose a binary classification task. When implemented with Neural Network based solutions, it is common to use the binary cross entropy (BCE) function as the loss to optimize. In this study, we propose a variant of BCE that enforces a margin in angular space and incorporate it in training the DeepPixBis model [1]. In addition, we also present a method to incorporate such a loss for attentive pixel wise supervision applicable in a fully convolutional setting. Our proposed approach achieves competitive scores in both intra and inter-dataset testing on multiple benchmark datasets, consistently outperforming vanilla DeepPixBis. Interestingly, in the case of Protocol 4 of OULU-NPU, considered to be the hardest protocol, our proposed method achieves 5.22% ACER, which is only 0.22% higher than the current State of the Art without requiring any expensive Neural Architecture Search.read more
Citations
More filters
Journal ArticleDOI
Revisiting Pixel-Wise Supervision for Face Anti-Spoofing
TL;DR: A novel pyramid supervision is proposed, which guides deep models to learn both local details and global semantics from multi-scale spatial context in face anti-spoofing, to improve the performance beyond existing pixel-wise supervision frameworks and enhance the model’s interpretability.
Posted Content
Revisiting Pixel-Wise Supervision for Face Anti-Spoofing
TL;DR: Zhang et al. as mentioned in this paper proposed a pyramid supervision for face anti-spoofing, which guides deep models to learn both local details and global semantics from multi-scale spatial context.
Journal ArticleDOI
Deep Learning for Face Anti-Spoofing: A Survey
TL;DR: In this paper , a comprehensive review of recent advances in deep learning based face anti-spoofing (FAS) is presented, which covers several novel and insightful components: 1) besides supervision with binary label (e.g., ‘0’ for bonafide vs. ‘1' for PAs), also investigate recent methods with pixel-wise supervision, and 2) in addition to traditional intra-dataset evaluation, collect and analyze the latest methods specially designed for domain generalization and open-set FAS; and 3) besides commercial RGB camera, summarize the deep learning applications under multi-modal (i.e. light field and flash) sensors.
Posted Content
Deep Learning for Face Anti-Spoofing: A Survey
TL;DR: A comprehensive review of recent advances in deep learning-based face anti-spoofing can be found in this article, which covers several novel and insightful components: 1) besides the traditional binary label (e.g., '0' for bonafide vs. '1' for PAs), they also investigate recent methods with pixel-wise supervision, and 2) in addition to traditional intra-dataset evaluation, they collect and analyze the latest methods specially designed for domain generalization and open-set FAS; and 3) besides commercial RGB camera, they summarize
Journal ArticleDOI
M3FAS: An Accurate and Robust MultiModal Mobile Face Anti-Spoofing System
TL;DR: Wang et al. as discussed by the authors designed a two-branch neural network with three hierarchical feature aggregation modules to perform cross-modal feature fusion and proposed a multi-head training strategy.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Proceedings ArticleDOI
FaceNet: A unified embedding for face recognition and clustering
TL;DR: A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
Proceedings ArticleDOI
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
TL;DR: This paper presents arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks, and shows that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead.
Proceedings ArticleDOI
SphereFace: Deep Hypersphere Embedding for Face Recognition
TL;DR: In this paper, the angular softmax (A-softmax) loss was proposed to learn angularly discriminative features for deep face recognition under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal interclass distance under a suitably chosen metric space.