Novelty detection aims at finding samples that differ in some form from the
distribution of seen samples. But not all changes are created equal. Data can
suffer a multitude of distribution shifts, and we might want to detect only
some types of relevant changes. Similar to works in out-of-distribution
generalization, we propose to use the formalization of separating into semantic
or content changes, that are relevant to our task, and style changes, that are
irrelevant. Within this formalization, we define the robust novelty detection
as the task of finding semantic changes while being robust to style
distributional shifts. Leveraging pretrained, large-scale model
representations, we introduce Stylist, a novel method that focuses on dropping
environment-biased features. First, we compute a per-feature score based on the
feature distribution distances between environments. Next, we show that our
selection manages to remove features responsible for spurious correlations and
improve novelty detection performance. For evaluation, we adapt domain
generalization datasets to our task and analyze the methods behaviors. We
additionally built a large synthetic dataset where we have control over the
spurious correlations degree. We prove that our selection mechanism improves
novelty detection algorithms across multiple datasets, containing both
stylistic and content shifts.

在这篇研究中，我们提出了一种名为 Stylist 的新方法，通过去除环境偏差特征来改进新颖性检测算法，从而检测与任务相关的语义变化并对抗风格分布的变化。我们证明了这种特征选择机制在包含风格和内容变化的多个数据集上改进了新颖性检测算法。

样式驱动的特征排序方法用于强鲁棒性新颖性检测

Stylist: Style-Driven Feature Ranking for Robust Novelty Detection

We tackle the problem of robust novelty detection, where we aim to detect
novelties in terms of semantic content while being invariant to changes in
other, irrelevant factors. Specifically, we operate in a setup with multiple
environments, where we determine the set of features that are associated more
with the environments, rather than to the content relevant for the task. Thus,
we propose a method that starts with a pretrained embedding and a multi-env
setup and manages to rank the features based on their environment-focus. First,
we compute a per-feature score based on the feature distribution variance
between envs. Next, we show that by dropping the highly scored ones, we manage
to remove spurious correlations and improve the overall performance by up to
6%, both in covariance and sub-population shift cases, both for a real and a
synthetic benchmark, that we introduce for this task.

我们提出了一种方法，利用预训练的嵌入和多环境设置，基于环境焦点对特征进行排名，以便在语义内容方面检测新奇性，并对无关因素变化进行不变性处理。通过计算特征在不同环境之间的分布方差，我们确定每个特征的得分，并通过丢弃得分高的特征来消除虚假相关性，在真实和合成基准测试中，我们的方法在协方差和子群体变化情况下提高了总体性能达 6%。