【论文阅读】Bag of Tricks for Efficient Text Classification

摘要

  • 这篇论文探索了一个简单有效的文本分类的baseline。
  • 实验表明快速文本分类器 f a s t T e x t fastText fastText 与深度学习分类器在准确度方面等价,并且训练和评估过程要快。
  • 他们能够用不到10分钟训练 f a s t T e x t fastText fastText 在超过10亿个单词上,并且用不到1分钟分类50万的句子在312000个类别上。

模型架构

  • 线性分类器在特征之间与类别之间不能共享参数。这可能会限制他们的泛化能力在大输出空间的背景下,当一些类别只有很少的例子时。一般的解决方法时分解这些线性分类器到一些低等级的矩阵或者使用多层神经网络。
    在这里插入图片描述
  • Figure1展示了一个简单的有等级约束的线性模型。第一个权重矩阵A时对单词的一个搜索表。将词表示平均后得到文章的表示,在反过来馈入一个线性分类器。文本表示是一个隐藏层的变量,它很可能会被重新使用。本文使用softmax函数来计算预定义类别的概率分布。对于一个集合的 N N N个文档,这会导致最小化各个类别的负对数似然:
    − 1 N ∑ n = 1 N y n l o g ( f ( B A x n ) ) -\frac{1}{N}\sum_{n=1}^{N}y_nlog(f(BAx_n)) N1n=1Nynlog(f(BAxn))
    式子中的 x n x_n xn是第 n n n个文档的标准化的bag特征, y n y_n yn是标签, A A A B B B是权重矩阵。这个模型在多CPU上进行异步的训练,使用随机梯度下降和一个线性衰退的学习率。

层级softmax

  • 当类别的数量很多时,使用线性分类器的计算成本太高。更精确的说,计算的复杂度为 O ( k h ) O(kh) O(kh) k k k时类别的数量, h h h时文本表示的维度。为了提升我们的运行时间,本文使用了一个基于哈夫曼编码树的层级softmax
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 1
    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.
评论 1
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