Bag of Tricks for Image Classification with Convolutional Neural Networks

项目地址:https://github.com/dmlc/gluon-cv

论文地址:http://openaccess.thecvf.com/content_CVPR_2019/papers/He_Bag_of_Tricks_for_Image_Classification_with_Convolutional_Neural_Networks_CVPR_2019_paper.pdf

摘要

       许多最近的进步在图像分类研究领域,归功于训练处理提炼,例如改变数据增加和优化方法。然而,在文献中,大多数改进不是简单地提到实现细节,就是只在源代码中可见。在这篇文章中,我们将考查一个集合在提炼和经验评估他们的影响在最后的模型精度上,通过消融研究。我们将展示,通过结合这些提炼在一起,我们能够明显地提高各种CNN模型。例如,我们提高ResNet-50的第一认证精度从75.3%到79.29%在ImageNet上。我们也证明提高在图像分类精度上导致较好的迁移学习性能在其它应用领域,例如目标检测和语义分割。

对比结果

                                   

总结

         在这篇文章中,我们研究了十几个技巧去训练深度卷积神经网络来提高模型精度。这些技巧引入细微的变化对模型的框架,数据预处理,损失函数,以及学习策略。我们的实验结果在ResNet-50,Iception-V3和MobileNet 表明这些技巧一致提高模型精度。比较兴奋地,堆积所有他们一起将会导致明显提高精度。另外,这些提高预训练模型显示强的优势在迁移学习,它提高目标检测和语义分割。

了解更多关于《计算机视觉与图形学》相关知识,请关注公众号:

下载我们视频中代码和相关讲义,请在公众号回复:计算机视觉课程资料

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Deep person re-identification is the task of recognizing a person across different camera views in a surveillance system. It is a challenging problem due to variations in lighting, pose, and occlusion. To address this problem, researchers have proposed various deep learning models that can learn discriminative features for person re-identification. However, achieving state-of-the-art performance often requires carefully designed training strategies and model architectures. One approach to improving the performance of deep person re-identification is to use a "bag of tricks" consisting of various techniques that have been shown to be effective in other computer vision tasks. These techniques include data augmentation, label smoothing, mixup, warm-up learning rates, and more. By combining these techniques, researchers have been able to achieve significant improvements in re-identification accuracy. In addition to using a bag of tricks, it is also important to establish a strong baseline for deep person re-identification. A strong baseline provides a foundation for future research and enables fair comparisons between different methods. A typical baseline for re-identification consists of a deep convolutional neural network (CNN) trained on a large-scale dataset such as Market-1501 or DukeMTMC-reID. The baseline should also include appropriate data preprocessing, such as resizing and normalization, and evaluation metrics, such as mean average precision (mAP) and cumulative matching characteristic (CMC) curves. Overall, combining a bag of tricks with a strong baseline can lead to significant improvements in deep person re-identification performance. This can have important practical applications in surveillance systems, where accurate person recognition is essential for ensuring public safety.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值