论文标题
在卷积神经网络中加剧了组装技术的性能改进
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
论文作者
论文摘要
图像分类的最新研究表明，用于改善卷积神经网络（CNN）的性能的各种技术。但是，尝试结合现有技术来创建实用模型的尝试仍然很少见。在这项研究中，我们进行了广泛的实验，以验证仔细组装这些技术并将其应用于基本CNN模型（例如Resnet和Mobilenet）可以提高模型的准确性和鲁棒性，同时最大程度地减少吞吐量的损失。我们提出的组装RESNET-50显示，TOP-1准确性从76.3 \％\％提高到82.78 \％，MCE从76.0 \％\％\％\％\％\％，MFR从57.7.7 \％\％\％\％\％\％\％\％\％\％\％\％\％\％。通过这些改进，推理吞吐量仅从536降低到312。为了验证转移学习的性能提高，在几个公共数据集上测试了细粒度的分类和图像检索任务，并表明改进了骨干网络性能的改善，可以显着提高转移学习绩效。我们的方法在2019年CVPR上获得了IFOOD竞争中的第一名，源代码和训练有素的模型可在https://github.com/clovaai/assembled-cnn上获得
Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still uncommon. In this study, we carry out extensive experiments to validate that carefully assembling these techniques and applying them to basic CNN models (e.g. ResNet and MobileNet) can improve the accuracy and robustness of the models while minimizing the loss of throughput. Our proposed assembled ResNet-50 shows improvements in top-1 accuracy from 76.3\% to 82.78\%, mCE from 76.0\% to 48.9\% and mFR from 57.7\% to 32.3\% on ILSVRC2012 validation set. With these improvements, inference throughput only decreases from 536 to 312. To verify the performance improvement in transfer learning, fine grained classification and image retrieval tasks were tested on several public datasets and showed that the improvement to backbone network performance boosted transfer learning performance significantly. Our approach achieved 1st place in the iFood Competition Fine-Grained Visual Recognition at CVPR 2019, and the source code and trained models are available at https://github.com/clovaai/assembled-cnn
