EnfoMax: Domain Entropy and Mutual Information Maximization for Domain Generalized Face Anti-spoofing

2023-02-17 · Tianyi Zheng

The face anti-spoofing (FAS) method performs well under intra-domain setups. However, its cross-domain performance is unsatisfactory. As a result, the domain generalization (DG) method has gained more attention in FAS. Existing methods treat FAS as a simple binary classification task and propose a heuristic training objective to learn domain-invariant features. However, there is no theoretical explanation of what a domain-invariant feature is. Additionally, the lack of theoretical support makes domain generalization techniques such as adversarial training lack training stability. To address these issues, this paper proposes the EnfoMax framework, which uses information theory to analyze cross-domain FAS tasks. This framework provides theoretical guarantees and optimization objectives for domain-generalized FAS tasks. EnfoMax maximizes the domain entropy and mutual information of live samples in source domains without using adversarial learning. Experimental results demonstrate that our approach performs well on extensive public datasets and outperforms state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2302.08674

Code (0)

등록된 구현이 없습니다.

Tasks

Binary Classification Contrastive Learning Domain Generalization Face Anti-Spoofing

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Adam 설명 없음

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

APS: Active Pretraining with Successor Features

2021-08-31 · Hao liu, Pieter Abbeel

We introduce a new unsupervised pretraining objective for reinforcement learning. During the unsupervised reward-free pretraining phase, the agent maximizes mutual information between tasks and states induced by the poli…

Unsupervised Reinforcement Learning

Submodular Benchmark Selection

2026-05-04 · Alexander Smola arxiv

Evaluating large language models across many benchmarks is expensive, yet many benchmarks are highly correlated. We formalize the selection of a small, informative subset as submodular maximization under a multivariate G…

Submodular Combinatorial Information Measures with Applications in Machine Learning

2020-06-27 · Rishabh Iyer, Ninad Khargonkar, Jeff Bilmes, Himanshu Asnani

Information-theoretic quantities like entropy and mutual information have found numerous uses in machine learning. It is well known that there is a strong connection between these entropic quantities and submodularity si…

BIG-bench Machine Learning Clustering Privacy Preserving

Information Maximization for Few-Shot Learning

2020-12-01 · NeurIPS 2020 12 · Malik Boudiaf, Imtiaz Ziko, Jérôme Rony, Jose Dolz 외

We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction …

Few-Shot Learning Meta-Learning

Transductive Information Maximization For Few-Shot Learning

2020-08-25 · Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony, José Dolz 외

Few-Shot Image Classification Few-Shot Learning Meta-Learning