Self-supervised learning (SSL) has achieved promising downstream performance. However, when facing various resource budgets in real-world applications, it costs a huge computation burden to pretrain multiple networks of various sizes one by one. In this paper, we propose Discriminative-SSL-based Slimmable Pretrained Networks (DSPNet), which can be trained at once and then slimmed to multiple sub-networks of various sizes, each of which faithfully learns good representation and can serve as good initialization for downstream tasks with various resource budgets. Specifically, we extend the idea of slimmable networks to a discriminative SSL paradigm, by integrating SSL and knowledge distillation gracefully. We show comparable or improved performance of DSPNet on ImageNet to the networks individually pretrained one by one under the linear evaluation and semi-supervised evaluation protocols, while reducing large training cost. The pretrained models also generalize well on downstream detection and segmentation tasks. Code will be made public.
翻译:自我监督的学习(SSL)取得了有希望的下游业绩。然而,在现实世界应用中面临各种资源预算时,它花费了巨大的计算负担来预先培训不同大小的多个网络。在本文中,我们提议了基于差异性SSL的基于自控的可升级的有限培训网络(DSPNet),这些网络可以一次性培训,然后细化为不同大小的多个子网络,每个小网络都忠实地学习了良好的代表性,并且可以作为各种资源预算下的下游任务的良好初始化。具体地说,我们通过将SSL和知识的精细提炼,将瘦化网络的概念推广到歧视性的SSL范式。我们展示了图像网络DSPNet的可比性或改进性能,在线性评价和半监督性评价协议下,先对网络进行单独培训,然后降低大型培训费用。预先培训的模式还将对下游探测和分解任务进行普及。守则将予公布。