arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.07529cs.LGcs.AI
收藏

Few-Shot类增量学习的软子网络研究

On the Soft-Subnetwork for Few-shot Class Incremental Learning

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院(KAIST))

Haeyong Kang, Jaehong Yoon, Sultan Rizky Hikmawan Madjid, Sung Ju Hwang, Chang D. Yoo

摘要:

受正则化彩票假说(RLTH)的启发,提出了一种Few-Shot类增量学习(FSCIL)方法,称为\emph{Soft-SubNetworks (SoftNet)} .我们的目标是增量地学习一系列会话,其中每个会话只包括每个类的几个训练实例,同时保留先前学习的知识。SoftNet在基础训练会话中联合学习模型权重和自适应非二进制软掩码,其中每个掩码由主要和次要子网络组成;前者旨在最大限度地减少训练期间的灾难性遗忘,后者旨在避免在每个新的训练会话中过度拟合到一些样本。我们提供了全面的实证验证,证明我们的SoftNet通过超越基准数据集的最先进基线性能,有效地解决了Few-Shot增量学习问题。

英文摘要:

Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothesizes that there exist smooth (non-binary) subnetworks within a dense network that achieve the competitive performance of the dense network, we propose a few-shot class incremental learning (FSCIL) method referred to as \emph{Soft-SubNetworks (SoftNet)}. Our objective is to learn a sequence of sessions incrementally, where each session only includes a few training instances per class while preserving the knowledge of the previously learned ones. SoftNet jointly learns the model weights and adaptive non-binary soft masks at a base training session in which each mask consists of the major and minor subnetwork; the former aims to minimize catastrophic forgetting during training, and the latter aims to avoid overfitting to a few samples in each new training session. We provide comprehensive empirical validations demonstrating that our SoftNet effectively tackles the few-shot incremental learning problem by surpassing the performance of state-of-the-art baselines over benchmark datasets.

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。

↑