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.

翻译：我们为重力生成网络提出了一个简单、灵活和有效的概念框架。我们的方法是一般性的,将目前两个独特和极为有效的Senet和CondConv统一成关于重量空间的同一框架。称为WeightNet的方法将两种方法笼统化,简单地在引力启动层增加一个又一个完全相连的分组层。我们使用完全由(组合的)完全相连的层组成的WeightNet直接输出卷发重量。WeightNet很容易,记忆保存在内核空间而不是特征空间上进行训练。由于灵活性,我们的方法优于图像网络和COCO探测任务的现有方法,实现了更好的精度-FLOPs和Acureacy-Parater交换。关于灵活重量空间的框架有可能进一步改进性能。代码可在https://github.com/megving-model/WeightNet上查阅。