An attribution-based pruning method for real-time mango detection with YOLO network
An attribution-based pruning method for real-time mango detection with YOLO network
复制标题
DOI：
10.1016/j.compag.2020.105214
复制
发表时间：
2020-02-01
影响因子：
8.3
通讯作者：
Yamaguchi, Yasushi
中科院分区：
文献类型：
--
作者：
Shi, Rui;Li, Tianxing;Yamaguchi, Yasushi
果园中水果的实时检测和定位对于产量估计、产量测绘和自动收获的农艺应用是必不可少的。传统的基于手工特征提取的检测方法很难适应实际果园环境的复杂变化。现代深度神经网络(DNN)需要高性能的计算单元来进行推理，这对于典型的农场和果园来说并不实用，尽管它具有很高的检测性能。为了降低DNN的计算量，我们提出了一种通用的属性剪枝方法，该方法可以很容易地对检测网络进行精调，从而能够准确地实时检测芒果。通过设计通道和空间掩码来推广属性方法，可以检测出原始YOLOv3-TING网络中与特定目标输出紧密相关的卷积核。然后，在通道维中逐层剪枝不相关的核。在对修剪后的网络进行微调之前，采用了锚点大小、数据增强和学习速率衰减来检测芒果。实验结果表明，提出的剪枝方法能够识别出与目标高度相关的卷积核函数，优化后的网络具有更好的芒果检测性能。我们得到的网络是一个尺度和旋转不变的芒果检测网络，具有2.6GFLOP(千兆浮点运算)，获得了0.944的F1-Score。与没有剪枝的精修网络相比，该网络的计算量减少了68.7%，而准确率提高了0.4%。与使用相同芒果数据集训练的最先进的网络相比，计算量减少了83.4%，而准确率仅损失了约2.4%。该剪枝方法可以从大规模的检测网络中剥离一个子网络，以满足移动设备对低功耗处理器的实时要求，例如ARM Cortex-A8执行大约4.0GFLOPS(千兆浮点运算/秒)。训练有素的网络和测试代码可用于比较研究。
Real-time fruit detection and localization in orchards are essential for agronomic applications of yield estimation, yield mapping, and automated harvesting. Traditional detection methods based on hand-crafted feature extractors are difficult to adapt to the complicated variations in real orchard environments. Modem deep neural networks (DNNs) need high performance computing units for inference, this is not practical for typical farms and orchards, despite the high detection performance. To reduce the computation cost of DNNs, we propose a generalized attribution method for pruning detection networks which can be easily finetuned to accurately detect mango in real time. By designing the channel and spatial masks to generalize the attribution method, the convolutional kernels that are firmly correlated with specific target output in the original YOLOv3-tiny network can be detected. Then, the uncorrelated kernels are pruned in channel-dimension layer-by-layer. Before finetuning the pruned network, anchor sizes, data augmentation, and learning rate decay were adapted for mango detection. The experimental results show that the proposed pruning method could identify the highly target-related convolutional kernels and that the finetuned network provides better mango detection performance than the original. Our resulting network which is a scale and rotation invariant mango detection network achieved an Fl-score of 0.944 with 2.6 GFLOPs (giga-floating point operations). Compared to the finetuned network without pruning, the computation of our network was reduced by 68.7% whereas the accuracy was increased by 0.4%. Compared to a state-of-the-art network trained with the same mango dataset, the computation was reduced by 83.4% with only about 2.4% loss in accuracy. The proposed pruning method can strip a sub-network from a large-scale detection network to meet the real-time requirements of low-power-consumption processors for mobile devices, e.g., ARM Cortex-A8 performs around 4.0 GFLOPS (giga-floating point operations per second). The trained network and test code are available for comparative studies.