The vision-language pre-training has enabled deep models to make a huge step
forward in generalizing across unseen domains. The recent learning method based
on the vision-language pre-training model is a great tool for domain
generalization and can solve this problem to a large extent. However, there are
still some issues that an advancement still suffers from trading-off between
domain invariance and class separability, which are crucial in current DG
problems. However, there are still some issues that an advancement still
suffers from trading-off between domain invariance and class separability,
which are crucial in current DG problems. In this paper, we introduce a novel
prompt learning strategy that leverages deep vision prompts to address domain
invariance while utilizing language prompts to ensure class separability,
coupled with adaptive weighting mechanisms to balance domain invariance and
class separability. Extensive experiments demonstrate that deep vision prompts
effectively extract domain-invariant features, significantly improving the
generalization ability of deep models and achieving state-of-the-art
performance on three datasets.

通过使用深度视觉提示以解决域不变性问题，结合语言提示以确保类别可分离性，以及自适应权重机制来平衡域不变性和类别可分离性，本文介绍了一种新的提示学习策略，并通过广泛实验证明深度视觉提示有效提取域不变特征，显著提高深度模型的泛化能力，在三个数据集上取得了最先进的性能。

跨域泛化的过渡式视觉 - 语言提示学习

Transitive Vision-Language Prompt Learning for Domain Generalization

This paper proposes an unsupervised method that leverages topological
characteristics of data manifolds to estimate class separability of the data
without requiring labels. Experiments conducted in this paper on several
datasets demonstrate a clear correlation and consistency between the class
separability estimated by the proposed method with supervised metrics like
Fisher Discriminant Ratio~(FDR) and cross-validation of a classifier, which
both require labels. This can enable implementing learning paradigms aimed at
learning from both labeled and unlabeled data, like semi-supervised and
transductive learning. This would be particularly useful when we have limited
labeled data and a relatively large unlabeled dataset that can be used to
enhance the learning process. The proposed method is implemented for language
model fine-tuning with automated stopping criterion by monitoring class
separability of the embedding-space manifold in an unsupervised setting. The
proposed methodology has been first validated on synthetic data, where the
results show a clear consistency between class separability estimated by the
proposed method and class separability computed by FDR. The method has been
also implemented on both public and internal data. The results show that the
proposed method can effectively aid -- without the need for labels -- a
decision on when to stop or continue the fine-tuning of a language model and
which fine-tuning iteration is expected to achieve a maximum classification
performance through quantification of the class separability of the embedding
manifold.

本文提出一种基于拓扑特征的无监督方法来预测数据的类别可分性，该方法适合于处理有限标注数据和大规模未标注数据的学习模型。通过实验证明，该方法与有监督的评估方法如 Fisher 判别比率和分类器的交叉验证有着一致的表现，可以有效地用于语言模型的 fine-tuning，并监控词向量空间中的嵌入流形，从而判断何时停止或继续 fine-tuning。

一种无监督数据集类分离度估计方法及其在 LLMs 微调中的应用

An Unsupervised Method for Estimating Class Separability of Datasets  with Application to LLMs Fine-Tuning

In discriminating between objects from different classes, the more separable
these classes are the less computationally expensive and complex a classifier
can be used. One thus seeks a measure that can quickly capture this
separability concept between classes whilst having an intuitive interpretation
on what it is quantifying. A previously proposed separability measure, the
separability index (SI) has been shown to intuitively capture the class
separability property very well. This short note highlights the limitations of
this measure and proposes a slight variation to it by combining it with another
form of separability measure that captures a quantity not covered by the
Separability Index.

介绍了用于测量类别可分性的指标的局限性，并提出了一种将另一种可分性指标与其结合的变体，以更好地评价分类器。