用梯度归因动态掩码，提升模型对未知类别的识别能力
Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation
- 基于模型梯度归因图动态掩码已学习特征，激发新特征学习
- 在多个数据集上超越现有方法，提升对未知类别和分布外样本的检测能力
- 适用于自监督学习与抗噪声鲁棒性场景，增强模型泛化性能
开放集识别（OSR）旨在模型推理时检测未知类别，尽管近期视觉模型已有进展，该问题仍具挑战。核心难点在于如何从有限数据中学习对未见类别有判别性的特征，而这些特征可能不具区分度。为此，本文提出GradMix，一种数据增强方法，在训练中动态利用模型的梯度归因图，对已学习概念进行掩码，促使模型从同一数据源中学习更全面的代表性特征。大量实验表明，该方法在开放集识别、闭集分类及分布外检测任务中均优于当前最优方法。此外，GradMix还能提升模型对各类噪声干扰的鲁棒性，并增强自监督学习下游分类性能，证明其在提升模型泛化能力方面的有效性。
原文摘要 · Abstract (English)
Open set recognition (OSR) is devised to address the problem of detecting novel classes during model inference. Even in recent vision models, this remains an open issue which is receiving increasing attention. Thereby, a crucial challenge is to learn features that are relevant for unseen categories from given data, for which these features might not be discriminative. To facilitate this process and "optimize to learn" more diverse features, we propose GradMix, a data augmentation method that dynamically leverages gradient-based attribution maps of the model during training to mask out already learned concepts. Thus GradMix encourages the model to learn a more complete set of representative features from the same data source. Extensive experiments on open set recognition, close set classification, and out-of-distribution detection reveal that our method can often outperform the state-of-the-art. GradMix can further increase model robustness to corruptions as well as downstream classification performance for self-supervised learning, indicating its benefit for model generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。