Basing on the analysis by revealing the equivalence of modern networks, we find that both ResNet and DenseNet are essentially derived from the same "dense topology", yet they only differ in the form of connection -- addition (dubbed "inner link") vs. concatenation (dubbed "outer link"). However, both two forms of connections have the superiority and insufficiency. To combine their advantages and avoid certain limitations on representation learning, we present a highly efficient and modularized Mixed Link Network (MixNet) which is equipped with flexible inner link and outer link modules. Consequently, ResNet, DenseNet and Dual Path Network (DPN) can be regarded as a special case of MixNet, respectively. Furthermore, we demonstrate that MixNets can achieve superior efficiency in parameter over the state-of-the-art architectures on many competitive datasets like CIFAR-10/100, SVHN and ImageNet.

基于现代网络等价性分析，我们发现ResNet和DenseNet本质上是从同一“紧密拓扑结构”派生而来的，只是连接形式不同-- 加法（称为“内连接”）vs连接（称为“外连接”）。然而，连接的两种形式都具有优势和不足之处。为了结合它们的优点并避免表示学习中的某些限制，我们提出了一种高效，模块化的混合连接网络（MixNet），它配备了灵活的内部连接和外部连接模块。因此，ResNet，DenseNet和Dual Path Network（DPN）分别可以视为MixNet的特殊情况。此外，我们证明MixNets在许多竞争数据集（如CIFAR-10/100，SVHN和ImageNet）上可以实现比最先进体系结构更高的参数效率。

混合链路网络