论文标题
驯鹿：重新访问体重网络的设计空间
WeightNet: Revisiting the Design Space of Weight Networks
论文作者
论文摘要
我们为重量生成网络提供了一个概念上简单，灵活和有效的框架。我们的方法是将当前的两个不同且极为有效的Senet和Condconv统一到体重空间的同一框架。该方法称为flownetnet，通过简单地将另外一个完全连接的层添加到注意力激活层来概括这两种方法。我们使用完全由（分组的）完全连接的层组成的flowtnet来直接输出卷积重量。 flowsnet易于训练，可以在内核空间而不是特征空间上进行训练。由于灵活性，我们的方法在ImageNet和可可检测任务上都优于现有方法，实现了更好的准确性流量和准确参数的权衡。灵活重量空间上的框架有可能进一步提高性能。代码可在https://github.com/megvii-model/weightnet上找到。
We present a conceptually simple, flexible and effective framework for weight generating networks. Our approach is general that unifies two current distinct and extremely effective SENet and CondConv into the same framework on weight space. The method, called WeightNet, generalizes the two methods by simply adding one more grouped fully-connected layer to the attention activation layer. We use the WeightNet, composed entirely of (grouped) fully-connected layers, to directly output the convolutional weight. WeightNet is easy and memory-conserving to train, on the kernel space instead of the feature space. Because of the flexibility, our method outperforms existing approaches on both ImageNet and COCO detection tasks, achieving better Accuracy-FLOPs and Accuracy-Parameter trade-offs. The framework on the flexible weight space has the potential to further improve the performance. Code is available at https://github.com/megvii-model/WeightNet.
