Yang Sen, Wang Xiaobao, Yang Qijuan, Dong Enzeng, Du Shengzhi
Tianjin Key Laboratory for Control Theory & Applications Complicated Systems, Tianjin University of Technology, Tianjin 300384, China.
China Mobile Communications Group Jiangsu Co., Ltd., Suqian Branch, Suqian 223800, China.
Sensors (Basel). 2022 Jun 10;22(12):4396. doi: 10.3390/s22124396.
The single batch normalization (BN) method is commonly used in the instance segmentation algorithms. The batch size is concerned with some drawbacks. A too small sample batch size leads to a sharp drop in accuracy, but a too large batch may result in the memory overflow of graphic processing units (GPU). These problems make BN not feasible to some instance segmentation tasks with inappropriate batch sizes. The self-adaptive normalization (SN) method, with an adaptive weight loss layer, shows good performance in instance segmentation algorithms, such as the YOLACT. However, the parameter averaging mechanism in the SN method is prone to problems in the weight learning and assignment process. In response to such a problem, the paper proposes to replace the single BN with an adaptive weight loss layer in SN models, based on which a weight learning method is developed. The proposed method increases the input feature expression ability of the subsequent layers. By building a Pytorch deep learning framework, the proposed method is validated in the MS-COCO data set and Autonomous Driving Cityscapes data set. The experimental results prove that the proposed method is effective in processing samples independent from the batch size. The stable accuracy for all kinds of target segmentation is achieved, and the overall loss value is significantly reduced at the same time. The convergence speed of the network is also improved.
单批归一化（BN）方法常用于实例分割算法中。批大小存在一些缺点。样本批大小过小会导致准确率急剧下降，但批大小过大可能会导致图形处理单元（GPU）内存溢出。这些问题使得BN在批大小不合适的某些实例分割任务中不可行。自适应归一化（SN）方法带有自适应权重损失层，在实例分割算法（如YOLACT）中表现出良好性能。然而，SN方法中的参数平均机制在权重学习和分配过程中容易出现问题。针对这一问题，本文提出在SN模型中用自适应权重损失层替换单BN，并在此基础上开发了一种权重学习方法。所提方法提高了后续层的输入特征表达能力。通过构建Pytorch深度学习框架，该方法在MS-COCO数据集和自动驾驶城市景观数据集中得到验证。实验结果证明，所提方法在处理与批大小无关的样本时是有效的。实现了各种目标分割的稳定准确率，同时整体损失值显著降低。网络的收敛速度也得到了提高。
