Open-world classification systems should discern out-of-distribution (OOD)
data whose labels deviate from those of in-distribution (ID) cases, motivating
recent studies in OOD detection. Advanced works, despite their promising
progress, may still fail in the open world, owing to the lack of knowledge
about unseen OOD data in advance. Although one can access auxiliary OOD data
(distinct from unseen ones) for model training, it remains to analyze how such
auxiliary data will work in the open world. To this end, we delve into such a
problem from a learning theory perspective, finding that the distribution
discrepancy between the auxiliary and the unseen real OOD data is the key to
affecting the open-world detection performance. Accordingly, we propose
Distributional-Augmented OOD Learning (DAL), alleviating the OOD distribution
discrepancy by crafting an OOD distribution set that contains all distributions
in a Wasserstein ball centered on the auxiliary OOD distribution. We justify
that the predictor trained over the worst OOD data in the ball can shrink the
OOD distribution discrepancy, thus improving the open-world detection
performance given only the auxiliary OOD data. We conduct extensive evaluations
across representative OOD detection setups, demonstrating the superiority of
our DAL over its advanced counterparts.

开放世界分类系统中，鉴别与内部分布不同的外部数据是一个重要问题，利用辅助外部数据进行模型训练可以改善开放世界检测性能。本文从学习理论的角度，通过构建一个包含辅助外部数据 Wasserstein 球中的全部分布的外部分布集，提出了分布增强的外部数据学习 (DAL) 方法，通过对球中的最差外部数据进行训练，缩小外部数据分布差异，从而提高开放世界检测性能。结果表明，DAL 在代表性的外部数据检测设置中具有优越性。

学习增加分布以进行外部分布检测

Learning to Augment Distributions for Out-of-Distribution Detection

Deep active learning (DAL) seeks to reduce annotation costs by enabling the
model to actively query instance annotations from which it expects to learn the
most. Despite extensive research, there is currently no standardized evaluation
protocol for transformer-based language models in the field of DAL. Diverse
experimental settings lead to difficulties in comparing research and deriving
recommendations for practitioners. To tackle this challenge, we propose the
ActiveGLAE benchmark, a comprehensive collection of data sets and evaluation
guidelines for assessing DAL. Our benchmark aims to facilitate and streamline
the evaluation process of novel DAL strategies. Additionally, we provide an
extensive overview of current practice in DAL with transformer-based language
models. We identify three key challenges - data set selection, model training,
and DAL settings - that pose difficulties in comparing query strategies. We
establish baseline results through an extensive set of experiments as a
reference point for evaluating future work. Based on our findings, we provide
guidelines for researchers and practitioners.

提出了 ActiveGLAE benchmark 作为评估 DAL 的综合数据集合和评估指南，并介绍了当前使用 Transformer-based 语言模型的 DAL 实践中存在的三个关键挑战 —— 数据集选择，模型培训和 DAL 设置，并在大量实验中建立了基线结果，以作为评估未来工作的参考点和为研究人员和实践者提供指南。

使用 Transformers 进行深度主动学习的基准测试 ActiveGLAE

ActiveGLAE: A Benchmark for Deep Active Learning with Transformers

We propose a new batch mode active learning algorithm designed for neural
networks and large query batch sizes. The method, Discriminative Active
Learning (DAL), poses active learning as a binary classification task,
attempting to choose examples to label in such a way as to make the labeled set
and the unlabeled pool indistinguishable. Experimenting on image classification
tasks, we empirically show our method to be on par with state of the art
methods in medium and large query batch sizes, while being simple to implement
and also extend to other domains besides classification tasks. Our experiments
also show that none of the state of the art methods of today are clearly better
than uncertainty sampling when the batch size is relatively large, negating
some of the reported results in the recent literature.

提出一种新的批次模式主动学习算法 —— 判别式主动学习法（DAL），并将其应用在神经网络和大批次查询的情境中，尝试通过将标记集合和未标记的数据池区分开来作为选择样本的依据来执行主动学习，结果表明我们的方法在中等和大批次查询中与最先进的方法相当，并且在实现简单的同时还可以扩展到除分类任务之外的其他领域，同时，我们的实验还表明在相对较大的批次中，当批量大小较大时，当前现有的最先进方法均不比不确定性采样明显更好，从而推翻了一些最近文献中报道的结果。