摘要
针对现有异常检测(Anomaly detection,AD)模型计算效率低和检测性能差等问题,提出一种多尺度流模型(Multi-scale normalizing flow,MS-Flow),通过多尺度交叉融合实现高效的视觉图像异常识别.具体地,在流模型(Nor-malizing flow,NF)内部构建层级式的多尺度架构来避免多通道数据的冗余交叉计算,同时保证网络的多尺度表达能力.此外,设计的层级感知模块通过逐层级的多粒度特征融合,在细粒度级别表达多尺度特征,有效地提高分布估计的精确性.该方法是一个平衡检测精度与计算效率的解决方案.在两个公开数据集上的实验表明,所提方法相较于以往的检测模型能够获得更高的检测精度(在 MVTec AD 和 BTAD 数据集上的平均 AUROC(Area under the receiver operating characteristics)分别为99.7％和96.0％),同时具有更高的计算效率,浮点运算次数(Floating point operations,FLOPs)约为CS-Flow的1/8.
Abstract
Aiming at the problems of low computational efficiency and poor detection performance of existing an-omaly detection(AD)models,a model called MS-Flow(multi-scale normalizing flow)is proposed to achieve highly efficient image anomaly recognition with multi-scale cross fusion.Specifically,a hierarchical multi-scale architecture is built inside normalizing flow(NF)to avoid redundant cross-computation of multi-channel data and to ensure the multi-scale representation capability.In addition,the proposed hierarchical perception module represents the multi-scale features at a granular level by fusing the multi-grained features layer by layer,which effectively improves the precision of distribution estimation.This approach is a solution that balances detection accuracy and computation-al efficiency.Experiments on two public datasets show that MS-Flow achieved higher detection accuracy and com-putational efficiency than previous detection models:The average AUROC(area under the receiver operating char-acteristics)on the MVTec AD and BTAD datasets are 99.7％and 96.0％,respectively,and the FLOPs(floating point operations)is about 1/8 of CS-Flow.
维普
万方数据