Abstract
In this paper, we aim at automatically searching an efficient network architecture for dense image prediction. Particularly, we follow the encoder-decoder style and focus on automatically designing a connectivity structure for the decoder. To achieve that, we first design a densely connected network with learnable connections named Fully Dense Network, which contains a large set of possible final connectivity structures. We then employ gradient descent to search the optimal connectivity from the dense connections. The search process is guided by a novel loss function, which pushes the weight of each connection to be binary and the connections to be sparse. The discovered connectivity achieves competitive results on two segmentation datasets, while runs more than three times faster and requires less than half parameters compared to state-of-the-art methods. An extensive experiment shows that the discovered connectivity is compatible with various backbones and generalizes well to other dense image prediction tasks.
Abstract (translated)
本文的目标是自动搜索一种高效的网络结构进行密集图像预测。特别是，我们遵循编码器-解码器的风格，重点是自动设计解码器的连接结构。为了实现这一点，我们首先设计了一个具有可学习连接的密集连接网络，称为完全密集网络，其中包含一组可能的最终连接结构。然后利用梯度下降法从密集连接中寻找最优连接。搜索过程由一个新的损失函数引导，该函数将每个连接的权重推为二进制，并将连接稀疏。发现的连接性在两个分割数据集上获得了竞争性的结果，同时运行速度超过三倍，与最先进的方法相比，所需参数不到一半。大量实验表明，所发现的连通性与各种主干网兼容，并能很好地推广到其它密集图像预测任务中。
URL
https://arxiv.org/abs/1904.07642
