One-Cycle Pruning: Pruning ConvNets Under a Tight Training Budget. (arXiv:2107.02086v3 [cs.CV] UPDATED)

Introducing sparsity in a neural network has been an efficient way to reduce
its complexity while keeping its performance almost intact. Most of the time,
sparsity is introduced using a three-stage pipeline: 1) train the model to
convergence, 2) prune the model according to some criterion, 3) fine-tune the
pruned model to recover performance. The last two steps are often performed
iteratively, leading to reasonable results but also to a time-consuming and
complex process. In our work, we propose to …

arxiv budget cv pruning training