Dynamic Channel Selection in Self-Supervised Learning
This addresses the need for faster inference in self-supervised computer vision models, though it is incremental as it adapts an existing method to a new context.
The paper tackled the problem of computational inefficiency in self-supervised learning models by applying a standard channel selection method from supervised learning to dynamically prune unnecessary channels, achieving comparable performance to the original network on image classification tasks (CIFAR-10, CIFAR-100, ImageNet-100) with significant reductions in FLOPs.
Whilst computer vision models built using self-supervised approaches are now commonplace, some important questions remain. Do self-supervised models learn highly redundant channel features? What if a self-supervised network could dynamically select the important channels and get rid of the unnecessary ones? Currently, convnets pre-trained with self-supervision have obtained comparable performance on downstream tasks in comparison to their supervised counterparts in computer vision. However, there are drawbacks to self-supervised models including their large numbers of parameters, computationally expensive training strategies and a clear need for faster inference on downstream tasks. In this work, our goal is to address the latter by studying how a standard channel selection method developed for supervised learning can be applied to networks trained with self-supervision. We validate our findings on a range of target budgets $t_{d}$ for channel computation on image classification task across different datasets, specifically CIFAR-10, CIFAR-100, and ImageNet-100, obtaining comparable performance to that of the original network when selecting all channels but at a significant reduction in computation reported in terms of FLOPs.