AugShuffleNet：多沟通，少计算
AugShuffleNet: Communicate More, Compute Less
摘要：
ShuffleNetV 2作为一个非常紧凑的模型，为设计高效的ConvNets提供了一个很好的例子，但它的局限性很少被注意到。在本文中，我们重新思考ShuffleNetV 2的设计模式，并发现通道的冗余问题仍然限制了Shuffle块的效率提高更广泛的ShuffleNetV 2。为了解决这个问题，我们提出了另一种增强变体的shuffle块的形式，类似于sock-like结构和更隐式的短连接。为了验证这个构建块的有效性，我们进一步构建了一个更强大，更高效的模型家族，称为AugShuffleNets。在CIFAR-10和CIFAR-100数据集上进行评估，AugShuffleNet在准确性方面始终优于ShuffleNetV 2，计算成本更低，参数数量更少。
英文摘要：
As a remarkable compact model, ShuffleNetV2 offers a good example to design efficient ConvNets but its limit is rarely noticed. In this paper, we rethink the design pattern of ShuffleNetV2 and find that the channel-wise redundancy problem still constrains the efficiency improvement of Shuffle block in the wider ShuffleNetV2. To resolve this issue, we propose another augmented variant of shuffle block in the form of bottleneck-like structure and more implicit short connections. To verify the effectiveness of this building block, we further build a more powerful and efficient model family, termed as AugShuffleNets. Evaluated on the CIFAR-10 and CIFAR-100 datasets, AugShuffleNet consistently outperforms ShuffleNetV2 in terms of accuracy with less computational cost and fewer parameter count.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
