当前位置: X-MOL 学术Comput. Electron. Agric. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Dual attention-guided feature pyramid network for instance segmentation of group pigs
Computers and Electronics in Agriculture ( IF 7.7 ) Pub Date : 2021-05-19 , DOI: 10.1016/j.compag.2021.106140
Zhiwei Hu , Hua Yang , Tiantian Lou

In respect of pig instance segmentation, the application of traditional computer vision techniques is constrained by sundries barrier, overlapping, and different perspectives in the pig breeding environment. In recent years, the attention-based methods have achieved remarkable performance. In this paper, we introduce two types of attention blocks into the feature pyramid network (FPN) (see nomenclature table) framework, which encode the semantic interdependencies in the channel (named channel attention block (CAB)) (see nomenclature table) and spatial (named spatial attention block (SAB)) (see nomenclature table) dimensions, respectively. By integrating the associated features, the CAB selectively emphasizes the interdependencies among the channels. Meanwhile, the SAB selectively aggregates the features at each position through a weighted sum of the features at all positions. A dual attention block (DAB) (see nomenclature table) is proposed to integrate CAB features with SAB information flexibly. A total of 45 pigs with 8 pens are captured as the experiment subjects. In comparison with such state-of-art attention modules as convolutional block attention module (CBAM) (see nomenclature table), bottleneck attention module (BAM) (see nomenclature table), and spatial-channel squeeze & excitation (SCSE) (see nomenclature table), embedding DAB can contribute to the most significant performance improvement in different task networks with distinct backbone networks. Especially with HTC-R101-DAB (hybrid task cascade) (see nomenclature table), the best performance is produced, with the AP0.5 (average precision) (see nomenclature table) AP0.75, AP0.5:0.95, and AP0.5:0.95-large reaching 93.1%, 84.1%, 69.4%, and 71.8%, respectively. Also, as indicated by ablation experiments, the SAB contributes more than CAB. Meanwhile, the predictive results appear a trend of increasing initially and decreasing afterwards after different numbers of SAB are merged. Besides, as revealed by the visualization of attention maps, attention blocks can extract regions with similar semantic information. The attention-based models also produce outstanding segmentation performance on public dataset, which evidences the practicability of our attention blocks. Our baseline models are available1.



中文翻译:

双重注意引导的特征金字塔网络,例如,群猪的分割

在猪实例分割方面,传统计算机视觉技术的应用受到猪繁殖环境中杂物屏障,重叠和不同视角的限制。近年来,基于注意力的方法取得了令人瞩目的性能。在本文中,我们将两种类型的注意块引入特征金字塔网络(FPN)(请参阅术语表)框架,以对通道(称为通道注意块(CAB))(请参阅术语表)和空间中的语义相互依赖性进行编码。 (称为空间注意区(SAB))(请参见术语表)尺寸。通过集成关联的功能,CAB有选择地强调了通道之间的相互依赖性。同时,SAB通过所有位置的特征的加权总和选择性地聚合每个位置的特征。提出了一个双注意块(DAB)(请参阅术语表),以灵活地将CAB功能与SAB信息集成在一起。总共捕获了45头8支猪的猪作为实验对象。与诸如卷积块注意模块(CBAM)(请参见术语表),瓶颈注意模块(BAM)(请参见术语表)和空间通道压缩和激励(SCSE)(请参见术语)等最新的关注模块进行比较表格),嵌入DAB有助于在具有不同骨干网的不同任务网络中实现最显着的性能改进。尤其是对于HTC-R101-DAB(混合任务级联)(请参阅术语表),使用AP可以产生最佳性能 提出了一个双注意块(DAB)(请参阅术语表),以灵活地将CAB功能与SAB信息集成在一起。总共捕获了8头猪的45头猪作为实验对象。与诸如卷积块注意模块(CBAM)(请参见术语表),瓶颈注意模块(BAM)(请参见术语表)和空间通道压缩和激励(SCSE)(请参见术语)等最新的关注模块进行比较表格),嵌入DAB有助于在具有不同骨干网的不同任务网络中实现最显着的性能改进。尤其是对于HTC-R101-DAB(混合任务级联)(请参阅术语表),使用AP可以产生最佳性能 提出了一个双注意块(DAB)(请参阅术语表),以灵活地将CAB功能与SAB信息集成在一起。总共捕获了45头8支猪的猪作为实验对象。与诸如卷积块注意模块(CBAM)(请参见术语表),瓶颈注意模块(BAM)(请参见术语表)和空间通道压缩和激励(SCSE)(请参见术语)等最新的关注模块进行比较表格),嵌入DAB有助于在具有不同骨干网的不同任务网络中实现最显着的性能改进。尤其是对于HTC-R101-DAB(混合任务级联)(请参阅术语表),使用AP可以产生最佳性能 与诸如卷积块注意模块(CBAM)(请参见术语表),瓶颈注意模块(BAM)(请参见术语表)和空间通道压缩和激励(SCSE)(请参见术语)等最新技术关注模块进行比较表格),嵌入DAB可以在具有不同骨干网的不同任务网络中最大程度地提高性能。尤其是对于HTC-R101-DAB(混合任务级联)(请参阅术语表),使用AP可以产生最佳性能 与诸如卷积块注意模块(CBAM)(请参见术语表),瓶颈注意模块(BAM)(请参见术语表)和空间通道压缩和激发(SCSE)(请参见术语)这样的最新关注模块进行比较表格),嵌入DAB有助于在具有不同骨干网的不同任务网络中实现最显着的性能改进。尤其是对于HTC-R101-DAB(混合任务级联)(请参阅术语表),使用AP可以产生最佳性能 嵌入DAB有助于在具有不同骨干网的不同任务网络中实现最显着的性能改进。尤其是对于HTC-R101-DAB(混合任务级联)(请参阅术语表),使用AP可以产生最佳性能 嵌入DAB可以有助于在具有不同骨干网的不同任务网络中实现最显着的性能改进。尤其是对于HTC-R101-DAB(混合任务级联)(请参阅术语表),使用AP可以产生最佳性能0.5(平均精度)(请参阅术语表)AP 0.75,AP 0.5:0.95和AP 0.5:0.95-大,分别达到93.1%,84.1%,69.4%和71.8%。而且,如消融实验所示,SAB的贡献要大于CAB。同时,合并不同数量的SAB后,预测结果呈现出先增加后减少的趋势。此外,正如注意力图的可视化所揭示的那样,注意力块可以提取具有相似语义信息的区域。基于注意力的模型还可以在公共数据集上产生出色的细分效果,这证明了我们的注意力块的实用性。我们的 基准模型可用1

更新日期:2021-05-19
down
wechat
bug