arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.04129cs.LGcs.CV
收藏

OVOR:基于虚拟异常正则化的单提示无排练类增量学习

OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning

Global Technology Applied Research(全球技术应用研究)

Wei-Cheng Huang, Chun-Fu Chen, Hsiang Hsu

AI总结:

本文提出基于虚拟异常正则化的单提示无排练类增量学习方法,简化提示机制,降低计算成本,提升分类准确性,在ImageNet-R和CIFAR-100上验证了有效性。

摘要:

近期研究表明,通过使用大型预训练模型和可学习提示,无排练的类增量学习(CIL)方法可以达到优于基于排练的著名方法的性能。无排练的CIL方法难以区分来自不同任务的类别,因为这些类别并未一起训练。在这项工作中,我们提出了一种基于虚拟异常的正则化方法,以收紧分类器的决策边界,从而缓解不同任务间类别的混淆。最近的基于提示的方法通常需要一个任务特定提示池,以防止新任务的知识覆盖先前任务的知识,这导致在查询和从池中组合适当提示时产生额外计算。如我们在论文中所揭示的,这种额外成本可以在不牺牲准确性的情况下消除。我们证明,一个简化的基于提示的方法可以达到与配备提示池的先前最先进(SOTA)方法相当的结果,同时使用更少的可学习参数和更低的推理成本。我们的正则化方法已证明与不同的基于提示的方法兼容,提升了那些先前的无排练SOTA CIL方法在ImageNet-R和CIFAR-100基准上的准确性。我们的源代码可在https://github.com/jpmorganchase/ovor获取。

英文摘要:

Recent works have shown that by using large pre-trained models along with learnable prompts, rehearsal-free methods for class-incremental learning (CIL) settings can achieve superior performance to prominent rehearsal-based ones. Rehearsal-free CIL methods struggle with distinguishing classes from different tasks, as those are not trained together. In this work we propose a regularization method based on virtual outliers to tighten decision boundaries of the classifier, such that confusion of classes among different tasks is mitigated. Recent prompt-based methods often require a pool of task-specific prompts, in order to prevent overwriting knowledge of previous tasks with that of the new task, leading to extra computation in querying and composing an appropriate prompt from the pool. This additional cost can be eliminated, without sacrificing accuracy, as we reveal in the paper. We illustrate that a simplified prompt-based method can achieve results comparable to previous state-of-the-art (SOTA) methods equipped with a prompt pool, using much less learnable parameters and lower inference cost. Our regularization method has demonstrated its compatibility with different prompt-based methods, boosting those previous SOTA rehearsal-free CIL methods' accuracy on the ImageNet-R and CIFAR-100 benchmarks. Our source code is available at https://github.com/jpmorganchase/ovor.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑