Channel pruning has been broadly recognized as an effective technique to
reduce the computation and memory cost of deep convolutional neural networks.
However, conventional pruning methods have limitations in that: they are
restricted to pruning process only, and they require a fully pre-trained large
model. Such limitations may lead to sub-optimal model quality as well as
excessive memory and training cost. In this paper, we propose a novel Channel
Exploration methodology, dubbed as CHEX, to rectify these problems. As opposed
to pruning-only strategy, we propose to repeatedly prune and regrow the
channels throughout the training process, which reduces the risk of pruning
important channels prematurely. More exactly: From intra-layer's aspect, we
tackle the channel pruning problem via a well known column subset selection
(CSS) formulation. From inter-layer's aspect, our regrowing stages open a path
for dynamically re-allocating the number of channels across all the layers
under a global channel sparsity constraint. In addition, all the exploration
process is done in a single training from scratch without the need of a
pre-trained large model. Experimental results demonstrate that CHEX can
effectively reduce the FLOPs of diverse CNN architectures on a variety of
computer vision tasks, including image classification, object detection,
instance segmentation, and 3D vision. For example, our compressed ResNet-50
model on ImageNet dataset achieves 76% top1 accuracy with only 25% FLOPs of the
original ResNet-50 model, outperforming previous state-of-the-art channel
pruning methods. The checkpoints and code are available at here .

提出了一种名为 CHEX 的新型通道探索方法，使用 CSS 解决层内的通道修剪问题，使用回归阶段解决层间的动态重新分配通道数量的问题。所有探索过程都是在单次训练中完成的，实验结果表明，CHEX 可以有效地减少各种 CNN 架构的 FLOPs，并在多种计算机视觉任务上表现出色。