Fair face recognition is all about learning invariant feature that
generalizes to unseen faces in any demographic group. Unfortunately, face
datasets inevitably capture the imbalanced demographic attributes that are
ubiquitous in real-world observations, and the model learns biased feature that
generalizes poorly in the minority group. We point out that the bias arises due
to the confounding demographic attributes, which mislead the model to capture
the spurious demographic-specific feature. The confounding effect can only be
removed by causal intervention, which requires the confounder annotations.
However, such annotations can be prohibitively expensive due to the diversity
of the demographic attributes. To tackle this, we propose to generate diverse
data partitions iteratively in an unsupervised fashion. Each data partition
acts as a self-annotated confounder, enabling our Invariant Feature
Regularization (INV-REG) to deconfound. INV-REG is orthogonal to existing
methods, and combining INV-REG with two strong baselines (Arcface and CIFP)
leads to new state-of-the-art that improves face recognition on a variety of
demographic groups. Code is available at
this https URL

公平人脸识别通过学习具有一般化效果的不变特征来应对真实世界观察中无偏常见的人口属性，其中存在偏差效应导致模型在少数群体中泛化效果不佳。我们指出这种偏差是由于潜在的人口属性导致不准确的特征学习，而这种混淆效应只能通过因果干预和消除潜在的人口属性才能解决。为了解决这个问题，我们提出了一种无监督生成多样性数据的分区方法，并结合两种强基准方法（Arcface 和 CIFP）与不变特征正则化（INV-REG）相结合，取得了新的最先进的结果，在各种人口群体中改善了人脸识别性能。

公平人脸识别的不变特征规范化

Invariant Feature Regularization for Fair Face Recognition

We investigate the limitations of random trials when the cause of interest is
confounded with the effect by formalizing a counterfactual policy-space where
the agent's natural predilection is input to a soft-intervention.

通过建立反事实政策空间，将代理者的内在偏好作为软干预的输入，研究了随机试验在因果混淆时的局限性。

受潜在混淆因素影响的序列反事实决策制定

Sequential Counterfactual Decision-Making Under Confounded Reward

Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate
shift and conditional shift assumptions, which essentially encourage models to
learn common features across domains. However, due to the lack of supervision
in the target domain, they suffer from the semantic loss: the feature will
inevitably lose non-discriminative semantics in source domain, which is however
discriminative in target domain. We use a causal view -- transportability
theory -- to identify that such loss is in fact a confounding effect, which can
only be removed by causal intervention. However, the theoretical solution
provided by transportability is far from practical for UDA, because it requires
the stratification and representation of the unobserved confounder that is the
cause of the domain gap. To this end, we propose a practical solution:
Transporting Causal Mechanisms (TCM), to identify the confounder stratum and
representations by using the domain-invariant disentangled causal mechanisms,
which are discovered in an unsupervised fashion. Our TCM is both theoretically
and empirically grounded. Extensive experiments show that TCM achieves
state-of-the-art performance on three challenging UDA benchmarks: ImageCLEF-DA,
Office-Home, and VisDA-2017. Codes are available in Appendix.

本文提出了一种实用的解决方案， Transporting Causal Mechanisms (TCM) ，通过使用无监督发现的领域不变分离的因果机制来识别混淆层和表示，从而解决了无监督域适应中的语义丢失问题，并在三个具有挑战性的 UDA 基准测试中取得了最先进的性能。

无监督领域自适应的因果机制传输

Transporting Causal Mechanisms for Unsupervised Domain Adaptation

We present a novel attention mechanism: Causal Attention (CATT), to remove
the ever-elusive confounding effect in existing attention-based vision-language
models. This effect causes harmful bias that misleads the attention module to
focus on the spurious correlations in training data, damaging the model
generalization. As the confounder is unobserved in general, we use the
front-door adjustment to realize the causal intervention, which does not
require any knowledge on the confounder. Specifically, CATT is implemented as a
combination of 1) In-Sample Attention (IS-ATT) and 2) Cross-Sample Attention
(CS-ATT), where the latter forcibly brings other samples into every IS-ATT,
mimicking the causal intervention. CATT abides by the Q-K-V convention and
hence can replace any attention module such as top-down attention and
self-attention in Transformers. CATT improves various popular attention-based
vision-language models by considerable margins. In particular, we show that
CATT has great potential in large-scale pre-training, e.g., it can promote the
lighter LXMERT~\cite{tan2019lxmert}, which uses fewer data and less
computational power, comparable to the heavier UNITER~\cite{chen2020uniter}.
Code is published in https://github.com/yangxuntu/catt.

本文提出了一种新颖的注意力机制 Causal Attention (CATT)，用于消除现有基于注意力的视觉语言模型中一直存在的混淆效应，CATT 可替换任何注意力模块，可大幅提高各种流行的注意力模型的性能，尤其在大规模预训练中具有潜力。