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.
翻译:设计适当的损失职能对于培训深层网络至关重要。特别是在语义分割领域,为各种不同的假设提出了各种评价指标。尽管广泛采用的跨热带损失及其变体取得了成功,但损失职能与评价指标之间的错配削弱了网络性能。与此同时,为每个具体指标设计人工设计损失职能需要专门知识和大量人力。在本文件中,我们提议通过搜索每个指标的不同替代损失来自动设计具体指标的损失职能。我们用参数化的功能来替代计量标准中的非区别操作,并进行参数搜索以优化损失表面的形状。引入了两种限制来规范搜索空间和使搜索效率得到提高。在PACAL VOC和城市景上进行的广泛实验表明,搜索的隐形损失比人工设计的损失功能一致。搜索的损失可以与其他数据集和网络相容。代码将解开。