arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07152cs.LGcs.CVcs.NEeess.IV
收藏

Move-to-Data:一种新的使用深度CNN的持续学习方法,用于图像类识别

Move-to-Data: A new Continual Learning approach with Deep CNNs, Application for image-class recognition

Univ. Bordeaux(波尔多大学);CNRS(法国国家科学研究中心);LaBRI(波尔多计算机科学实验室);INCIA(认知神经科学与整合研究中心)

Miltiadis Poursanidis, Jenny Benois-Pineau, Akka Zemmari, Boris Mansenca, Aymar de Rugy

摘要:

在应用监督学习方法的许多现实任务中,所有的训练数据不是同时可用的。这些例子是终身图像分类或在仪器人员与其环境交互期间识别环境对象,用更多图像丰富在线数据库。有必要在“训练记录阶段”对模型进行预训练,然后根据新的数据进行调整。这就是渐进式/持续学习方法的任务。在这些方法要解决的不同问题中,例如在模型中引入新的类别,将现有类别细化为子类别,并将训练好的分类器扩展到它们,...我们集中于用现有类别的新的附加训练数据调整预训练模型的问题。我们提出了一个快速的持续学习层在神经元网络的末端。所获得的结果在开源CIFAR基准数据集上进行了说明。所提出的计划产生类似的再训练性能,但大大降低了计算成本。

英文摘要:

In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of instrumented persons with their environment, enrichment of an online-database with more images. It is necessary to pre-train the model at a "training recording phase" and then adjust it to the new coming data. This is the task of incremental/continual learning approaches. Amongst different problems to be solved by these approaches such as introduction of new categories in the model, refining existing categories to sub-categories and extending trained classifiers over them, ... we focus on the problem of adjusting pre-trained model with new additional training data for existing categories. We propose a fast continual learning layer at the end of the neuronal network. Obtained results are illustrated on the opensource CIFAR benchmark dataset. The proposed scheme yields similar performances as retraining but with drastically lower computational cost.

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。

↑