论文标题
自动seg-loss：搜索度量代理以获取语义细分
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
论文作者
论文摘要
设计适当的损失功能对于训练深层网络至关重要。特别是在语义细分领域，已经提出了各种评估指标。尽管广泛采用的交叉渗透损失及其变体取得了成功，但损失函数和评估指标之间的错误对准会降低网络性能。同时，为每个特定度量的手动设计损失功能需要专业知识和重要的人力。在本文中，我们建议通过为每个度量搜索可区分的替代损失来自动化指标特异性损耗函数的设计。我们在具有参数化函数的指标中代替非差异操作，并进行参数搜索以优化损失表面的形状。引入了两个约束，以使搜索空间正规化并提高搜索。关于Pascal VOC和CityScapes的广泛实验表明，搜索的替代损失的表现始终超过手动设计的损失功能。搜索的损失可以很好地推广到其他数据集和网络。代码应发布。
Designing proper loss functions is essential in training deep networks. Especially in the field of semantic segmentation, various evaluation metrics have been proposed for diverse scenarios. Despite the success of the widely adopted cross-entropy loss and its variants, the mis-alignment between the loss functions and evaluation metrics degrades the network performance. Meanwhile, manually designing loss functions for each specific metric requires expertise and significant manpower. In this paper, we propose to automate the design of metric-specific loss functions by searching differentiable surrogate losses for each metric. We substitute the non-differentiable operations in the metrics with parameterized functions, and conduct parameter search to optimize the shape of loss surfaces. Two constraints are introduced to regularize the search space and make the search efficient. Extensive experiments on PASCAL VOC and Cityscapes demonstrate that the searched surrogate losses outperform the manually designed loss functions consistently. The searched losses can generalize well to other datasets and networks. Code shall be released.
