تقرير
GAN Memory with No Forgetting
| العنوان: | GAN Memory with No Forgetting |
|---|---|
| المؤلفون: | Cong, Yulai, Zhao, Miaoyun, Li, Jianqiao, Wang, Sijia, Carin, Lawrence |
| سنة النشر: | 2020 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning |
| الوصف: | As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected. Motivated by that, we propose a GAN memory for lifelong learning, which is capable of remembering a stream of datasets via generative processes, with \emph{no} forgetting. Our GAN memory is based on recognizing that one can modulate the "style" of a GAN model to form perceptually-distant targeted generation. Accordingly, we propose to do sequential style modulations atop a well-behaved base GAN model, to form sequential targeted generative models, while simultaneously benefiting from the transferred base knowledge. The GAN memory -- that is motivated by lifelong learning -- is therefore itself manifested by a form of lifelong learning, via forward transfer and modulation of information from prior tasks. Experiments demonstrate the superiority of our method over existing approaches and its effectiveness in alleviating catastrophic forgetting for lifelong classification problems. Code is available at https://github.com/MiaoyunZhao/GANmemory_LifelongLearning. Comment: NeurIPS2020 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2006.07543 |
| رقم الأكسشن: | edsarx.2006.07543 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |