Recently, convolutional neural networks (CNNs) have achieved great success in computer vision, but suffer from parameter redundancy in large-scale networks. DenseNet is a typical CNN architecture, which connects each layer to every other layer to maximize feature reuse and network efficiency, but it can become parametrically expensive with the potential risk of overfitting in deep networks. To address these problems, we propose a lightweight Densely Connected and Inter-Sparse Convolutional Networks with aggregated Squeeze-and-Excitation transformations (DenisNet-SE) in this paper. First, Squeeze-and-Excitation (SE) blocks are introduced in different locations of the dense model to adaptively recalibrate channel-wise feature responses. Meanwhile, we propose the Squeeze-Excitation-Residual (SERE) block, which applies residual learning to construct identity mapping. Second, to construct the densely connected and inter-sparse structure, we further apply the sparse three-layer bottleneck layer and grouped convolutions, which increase the cardinality of transformations. Our proposed network is evaluated on three highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, and ImageNet) and achieves better performance than the state-of-the-art networks while requiring fewer parameters.

最近，卷积神经网络（CNN）在计算机视觉方面取得了巨大的成功，但是在大规模网络中却存在参数冗余的问题。DenseNet是一种典型的CNN架构，该架构将每一层连接到其他每一层，以最大程度地实现功能复用和网络效率，但它在参数上可能会变得昂贵，并且可能会过度适合深度网络。为了解决这些问题，我们在本文中提出了一种轻量级的密集连接和稀疏卷积网络，该网络具有聚合的挤压和激发变换（DenisNet-SE）。首先，在密集模型的不同位置引入挤压和激励（SE）块，以自适应地重新校准通道级特征响应。同时，我们提出了“挤压-激励-残余”（SERE）块，应用残余学习来构造身份映射。其次，为了构造密集连接和稀疏的结构，我们进一步应用稀疏的三层瓶颈层和分组卷积，这增加了变换的基数。我们提出的网络在三个竞争激烈的对象识别基准测试任务（CIFAR-10，CIFAR-100和ImageNet）上进行了评估，并且与现有网络相比，其性能要求更高，同时所需参数更少。