Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Previous solutions to this problem rely mainly on knowledge distillation, which involves a two-stage procedure: first training a large teacher model and then distilling it to improve the generalization ability of smaller ones. In this work, we present a one-stage solution to obtain pre-trained small models without the need for extra teachers, namely, slimmable networks for contrastive self-supervised learning (\emph{SlimCLR}). A slimmable network consists of a full network and several weight-sharing sub-networks, which can be pre-trained once to obtain various networks, including small ones with low computation costs. However, interference between weight-sharing networks leads to severe performance degradation in self-supervised cases, as evidenced by \emph{gradient magnitude imbalance} and \emph{gradient direction divergence}. The former indicates that a small proportion of parameters produce dominant gradients during backpropagation, while the main parameters may not be fully optimized. The latter shows that the gradient direction is disordered, and the optimization process is unstable. To address these issues, we introduce three techniques to make the main parameters produce dominant gradients and sub-networks have consistent outputs. These techniques include slow start training of sub-networks, online distillation, and loss re-weighting according to model sizes. Furthermore, theoretical results are presented to demonstrate that a single slimmable linear layer is sub-optimal during linear evaluation. Thus a switchable linear probe layer is applied during linear evaluation. We instantiate SlimCLR with typical contrastive learning frameworks and achieve better performance than previous arts with fewer parameters and FLOPs.
翻译:暂无翻译