Multi-scale features are essential for dense prediction tasks, including object detection, instance segmentation, and semantic segmentation. Existing state-of-the-art methods usually first extract multi-scale features by a classification backbone and then fuse these features by a lightweight module (e.g. the fusion module in FPN). However, we argue that it may not be sufficient to fuse the multi-scale features through such a paradigm, because the parameters allocated for feature fusion are limited compared with the heavy classification backbone. In order to address this issue, we propose a new architecture named Cascade Fusion Network (CFNet) for dense prediction. Besides the stem and several blocks used to extract initial high-resolution features, we introduce several cascaded stages to generate multi-scale features in CFNet. Each stage includes a sub-backbone for feature extraction and an extremely lightweight transition block for feature integration. This design makes it possible to fuse features more deeply and effectively with a large proportion of parameters of the whole backbone. Extensive experiments on object detection, instance segmentation, and semantic segmentation validated the effectiveness of the proposed CFNet. Codes will be available at https://github.com/zhanggang001/CFNet.
翻译:多尺度特征对于密集的预测任务至关重要,包括物体探测、试样分割和语义分割。现有的先进方法通常先通过分类主干提取多尺度特征,然后通过轻量级模块(例如FPN的聚变模块)将这些特征连接起来。然而,我们认为,它可能不足以通过这种模式使多尺度特征融合起来,因为为特性融合分配的参数与重质分类主干相比是有限的。为了解决这一问题,我们提议了一个新的结构,名称为Cascade Fusion网络(CFNet),用于密集预测。除了用于提取初始高分辨率特征的干线和若干块外,我们还采用几个级联级阶段,在CFNet中生成多尺度特征。每个阶段都包括用于特征提取的子脊椎和极轻质转换块。这一设计使得为特性融合而分配的参数比重更深和有效结合整个骨干大的一部分参数。关于对象探测、实例分割和语义分割的大规模实验,验证了拟议的CFFNet的效能。CFMCM/SM.CM. 将可在 http://giangs.M.S.