基于收敛模拟驱动搜索的目标检测损失函数发现
Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search
摘要：
为视觉任务设计合适的损失函数是提高现有模型性能的一个长期研究方向。对于目标检测，通过考虑不同的学习挑战，精心设计了完善的分类和回归损失函数。受网络结构搜索的最新进展的启发，探索通过直接搜索原始操作组合来发现新的损失函数公式的可能性是有趣的。从而使学习的损失不仅适合于不同的目标检测挑战，以减轻巨大的人力，但也有更好的对齐与评价指标和良好的数学收敛性能。除了以前的自动损失工作的人脸识别和图像分类，我们的工作首次尝试发现新的损失函数具有挑战性的目标检测从原始的操作水平。我们提出了一种有效的收敛模拟驱动的进化搜索算法，称为CSE-Autoloss，通过收敛性验证和模型优化模拟来规范损失候选的数学合理性，从而加快搜索进度。CSE-Autoloss涉及的搜索空间涵盖了现有损失的各种可能的变体，并在短时间内（约1.5个挂钟日）发现搜索最佳的损失函数组合。我们对流行检测器上的损失函数搜索进行了广泛的评估，并验证了在不同架构和数据集上搜索损失的良好泛化能力。我们的实验表明，最佳发现的损失函数组合优于默认组合的1.1%和0.8%的mAP方面的两阶段和一阶段检测器COCO分别。我们的搜索损失可在https://github.com/PerdonLiu/CSE-Autoloss上找到。
英文摘要：
Designing proper loss functions for vision tasks has been a long-standing research direction to advance the capability of existing models. For object detection, the well-established classification and regression loss functions have been carefully designed by considering diverse learning challenges. Inspired by the recent progress in network architecture search, it is interesting to explore the possibility of discovering new loss function formulations via directly searching the primitive operation combinations. So that the learned losses not only fit for diverse object detection challenges to alleviate huge human efforts, but also have better alignment with evaluation metric and good mathematical convergence property. Beyond the previous auto-loss works on face recognition and image classification, our work makes the first attempt to discover new loss functions for the challenging object detection from primitive operation levels. We propose an effective convergence-simulation driven evolutionary search algorithm, called CSE-Autoloss, for speeding up the search progress by regularizing the mathematical rationality of loss candidates via convergence property verification and model optimization simulation. CSE-Autoloss involves the search space that cover a wide range of the possible variants of existing losses and discovers best-searched loss function combination within a short time (around 1.5 wall-clock days). We conduct extensive evaluations of loss function search on popular detectors and validate the good generalization capability of searched losses across diverse architectures and datasets. Our experiments show that the best-discovered loss function combinations outperform default combinations by 1.1% and 0.8% in terms of mAP for two-stage and one-stage detectors on COCO respectively. Our searched losses are available at https://github.com/PerdonLiu/CSE-Autoloss.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
