论文标题
MRF-UNETS：Markov随机字段搜索UNET
MRF-UNets: Searching UNet with Markov Random Fields
论文作者
论文摘要
UNET [27]由于其简单性和有效性而被广泛用于语义分割。但是，其手动设计的体系结构应用于没有架构优化的大量问题设置，或者使用手动调整，这很耗时，并且可以是最佳的。在这项工作中，首先，我们提出了Markov随机场神经体系结构搜索（MRF-NAS），该搜索扩展并改善了最新的自适应和最佳网络宽度搜索（AOWS）方法[4] [4]（i）（i）更一般的MRF框架（II）多样化的M-Pest Loopy推断（III）可不同的参数。这提供了必要的NAS框架，以有效探索诱导Loopopy推理图的网络体系结构，包括由跳过连接引起的循环。以UNET为骨干，我们找到了一个建筑MRF-UNET，该体系结构显示了几个有趣的特征。其次，通过这些特征的镜头，我们确定了原始UNET架构的子次要性，并通过MRF-UNETV2进一步改善了我们的结果。实验表明，我们的MRF-UNET在三个航空图像数据集和两个医疗图像数据集上的表现明显优于几个基准，同时保持低计算成本。该代码可在以下网址提供：https：//github.com/zifuwanggg/mrf-unets。
UNet [27] is widely used in semantic segmentation due to its simplicity and effectiveness. However, its manually-designed architecture is applied to a large number of problem settings, either with no architecture optimizations, or with manual tuning, which is time consuming and can be sub-optimal. In this work, firstly, we propose Markov Random Field Neural Architecture Search (MRF-NAS) that extends and improves the recent Adaptive and Optimal Network Width Search (AOWS) method [4] with (i) a more general MRF framework (ii) diverse M-best loopy inference (iii) differentiable parameter learning. This provides the necessary NAS framework to efficiently explore network architectures that induce loopy inference graphs, including loops that arise from skip connections. With UNet as the backbone, we find an architecture, MRF-UNet, that shows several interesting characteristics. Secondly, through the lens of these characteristics, we identify the sub-optimality of the original UNet architecture and further improve our results with MRF-UNetV2. Experiments show that our MRF-UNets significantly outperform several benchmarks on three aerial image datasets and two medical image datasets while maintaining low computational costs. The code is available at: https://github.com/zifuwanggg/MRF-UNets.
